diff --git a/python/.pre-commit-config.yaml b/python/.pre-commit-config.yaml
index 8a8b31418e8c..cf56bc31620a 100644
--- a/python/.pre-commit-config.yaml
+++ b/python/.pre-commit-config.yaml
@@ -54,4 +54,4 @@ repos:
     rev: '4.0.1'
     hooks:
       - id: flake8
-        args: [ "--ignore=E501,W503" ]
+        args: [ "--ignore=E501,W503,E203" ]
diff --git a/python/LICENSE b/python/LICENSE
index 7868b9b44048..5823c32b65e0 100644
--- a/python/LICENSE
+++ b/python/LICENSE
@@ -202,3 +202,14 @@
    limitations under the License.
 
 --------------------------------------------------------------------------------
+
+This product includes code from Apache Avro.
+
+* Code for initializing the Avro (de)compression codecs
+* The Binary decoder for reading in an Avro byte stream
+
+Copyright: 2014-2022 The Apache Software Foundation.
+Home page: https://avro.apache.org/
+License: https://www.apache.org/licenses/LICENSE-2.0
+
+--------------------------------------------------------------------------------
diff --git a/python/poetry.lock b/python/poetry.lock
index 0feeb1f76f28..91dfbc691400 100644
--- a/python/poetry.lock
+++ b/python/poetry.lock
@@ -20,6 +20,17 @@ docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
 tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
 tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "cloudpickle"]
 
+[[package]]
+name = "cffi"
+version = "1.15.0"
+description = "Foreign Function Interface for Python calling C code."
+category = "main"
+optional = true
+python-versions = "*"
+
+[package.dependencies]
+pycparser = "*"
+
 [[package]]
 name = "cfgv"
 version = "3.3.1"
@@ -38,14 +49,14 @@ python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
 [[package]]
 name = "coverage"
-version = "6.4"
+version = "6.4.1"
 description = "Code coverage measurement for Python"
 category = "dev"
 optional = false
 python-versions = ">=3.7"
 
 [package.dependencies]
-tomli = {version = "*", optional = true, markers = "python_version < \"3.11\" and extra == \"toml\""}
+tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.11.0a6\" and extra == \"toml\""}
 
 [package.extras]
 toml = ["tomli"]
@@ -66,6 +77,20 @@ category = "dev"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
+[[package]]
+name = "fastavro"
+version = "1.5.1"
+description = "Fast read/write of AVRO files"
+category = "dev"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+codecs = ["python-snappy", "zstandard", "lz4"]
+lz4 = ["lz4"]
+snappy = ["python-snappy"]
+zstandard = ["zstandard"]
+
 [[package]]
 name = "filelock"
 version = "3.7.1"
@@ -218,6 +243,14 @@ python-versions = ">=3.7"
 [package.dependencies]
 numpy = ">=1.16.6"
 
+[[package]]
+name = "pycparser"
+version = "2.21"
+description = "C parser in Python"
+category = "main"
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
 [[package]]
 name = "pyparsing"
 version = "3.0.9"
@@ -267,6 +300,14 @@ pep517 = "*"
 docs = ["sphinx", "jaraco.packaging (>=8.2)", "rst.linker (>=1.9)"]
 testing = ["pytest (>=4.6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "types-docutils", "pytest-black (>=0.3.7)", "pytest-mypy"]
 
+[[package]]
+name = "python-snappy"
+version = "0.6.1"
+description = "Python library for the snappy compression library from Google"
+category = "main"
+optional = true
+python-versions = "*"
+
 [[package]]
 name = "pyyaml"
 version = "6.0"
@@ -329,13 +370,29 @@ python-versions = ">=3.7"
 docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)"]
 testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "jaraco.itertools", "func-timeout", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
 
+[[package]]
+name = "zstandard"
+version = "0.17.0"
+description = "Zstandard bindings for Python"
+category = "main"
+optional = true
+python-versions = ">=3.6"
+
+[package.dependencies]
+cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\""}
+
+[package.extras]
+cffi = ["cffi (>=1.11)"]
+
 [extras]
 pyarrow = ["pyarrow"]
+python-snappy = ["zstandard"]
+snappy = ["python-snappy"]
 
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.8"
-content-hash = "3e07f5fb1c8f204b0a004541776b7d90cad2afac926c2c8554df599b977429e9"
+content-hash = "439429e65911b8e768bd4617a4883e8a4ec2652df3a43b28755346da8ed17e19"
 
 [metadata.files]
 atomicwrites = [
@@ -346,6 +403,58 @@ attrs = [
     {file = "attrs-21.4.0-py2.py3-none-any.whl", hash = "sha256:2d27e3784d7a565d36ab851fe94887c5eccd6a463168875832a1be79c82828b4"},
     {file = "attrs-21.4.0.tar.gz", hash = "sha256:626ba8234211db98e869df76230a137c4c40a12d72445c45d5f5b716f076e2fd"},
 ]
+cffi = [
+    {file = "cffi-1.15.0-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:c2502a1a03b6312837279c8c1bd3ebedf6c12c4228ddbad40912d671ccc8a962"},
+    {file = "cffi-1.15.0-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:23cfe892bd5dd8941608f93348c0737e369e51c100d03718f108bf1add7bd6d0"},
+    {file = "cffi-1.15.0-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:41d45de54cd277a7878919867c0f08b0cf817605e4eb94093e7516505d3c8d14"},
+    {file = "cffi-1.15.0-cp27-cp27m-win32.whl", hash = "sha256:4a306fa632e8f0928956a41fa8e1d6243c71e7eb59ffbd165fc0b41e316b2474"},
+    {file = "cffi-1.15.0-cp27-cp27m-win_amd64.whl", hash = "sha256:e7022a66d9b55e93e1a845d8c9eba2a1bebd4966cd8bfc25d9cd07d515b33fa6"},
+    {file = "cffi-1.15.0-cp27-cp27mu-manylinux1_i686.whl", hash = "sha256:14cd121ea63ecdae71efa69c15c5543a4b5fbcd0bbe2aad864baca0063cecf27"},
+    {file = "cffi-1.15.0-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:d4d692a89c5cf08a8557fdeb329b82e7bf609aadfaed6c0d79f5a449a3c7c023"},
+    {file = "cffi-1.15.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0104fb5ae2391d46a4cb082abdd5c69ea4eab79d8d44eaaf79f1b1fd806ee4c2"},
+    {file = "cffi-1.15.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:91ec59c33514b7c7559a6acda53bbfe1b283949c34fe7440bcf917f96ac0723e"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f5c7150ad32ba43a07c4479f40241756145a1f03b43480e058cfd862bf5041c7"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:00c878c90cb53ccfaae6b8bc18ad05d2036553e6d9d1d9dbcf323bbe83854ca3"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:abb9a20a72ac4e0fdb50dae135ba5e77880518e742077ced47eb1499e29a443c"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a5263e363c27b653a90078143adb3d076c1a748ec9ecc78ea2fb916f9b861962"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f54a64f8b0c8ff0b64d18aa76675262e1700f3995182267998c31ae974fbc382"},
+    {file = "cffi-1.15.0-cp310-cp310-win32.whl", hash = "sha256:c21c9e3896c23007803a875460fb786118f0cdd4434359577ea25eb556e34c55"},
+    {file = "cffi-1.15.0-cp310-cp310-win_amd64.whl", hash = "sha256:5e069f72d497312b24fcc02073d70cb989045d1c91cbd53979366077959933e0"},
+    {file = "cffi-1.15.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:64d4ec9f448dfe041705426000cc13e34e6e5bb13736e9fd62e34a0b0c41566e"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2756c88cbb94231c7a147402476be2c4df2f6078099a6f4a480d239a8817ae39"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3b96a311ac60a3f6be21d2572e46ce67f09abcf4d09344c49274eb9e0bf345fc"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:75e4024375654472cc27e91cbe9eaa08567f7fbdf822638be2814ce059f58032"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:59888172256cac5629e60e72e86598027aca6bf01fa2465bdb676d37636573e8"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:27c219baf94952ae9d50ec19651a687b826792055353d07648a5695413e0c605"},
+    {file = "cffi-1.15.0-cp36-cp36m-win32.whl", hash = "sha256:4958391dbd6249d7ad855b9ca88fae690783a6be9e86df65865058ed81fc860e"},
+    {file = "cffi-1.15.0-cp36-cp36m-win_amd64.whl", hash = "sha256:f6f824dc3bce0edab5f427efcfb1d63ee75b6fcb7282900ccaf925be84efb0fc"},
+    {file = "cffi-1.15.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:06c48159c1abed75c2e721b1715c379fa3200c7784271b3c46df01383b593636"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c2051981a968d7de9dd2d7b87bcb9c939c74a34626a6e2f8181455dd49ed69e4"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:fd8a250edc26254fe5b33be00402e6d287f562b6a5b2152dec302fa15bb3e997"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91d77d2a782be4274da750752bb1650a97bfd8f291022b379bb8e01c66b4e96b"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:45db3a33139e9c8f7c09234b5784a5e33d31fd6907800b316decad50af323ff2"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:263cc3d821c4ab2213cbe8cd8b355a7f72a8324577dc865ef98487c1aeee2bc7"},
+    {file = "cffi-1.15.0-cp37-cp37m-win32.whl", hash = "sha256:17771976e82e9f94976180f76468546834d22a7cc404b17c22df2a2c81db0c66"},
+    {file = "cffi-1.15.0-cp37-cp37m-win_amd64.whl", hash = "sha256:3415c89f9204ee60cd09b235810be700e993e343a408693e80ce7f6a40108029"},
+    {file = "cffi-1.15.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4238e6dab5d6a8ba812de994bbb0a79bddbdf80994e4ce802b6f6f3142fcc880"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0808014eb713677ec1292301ea4c81ad277b6cdf2fdd90fd540af98c0b101d20"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:57e9ac9ccc3101fac9d6014fba037473e4358ef4e89f8e181f8951a2c0162024"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b6c2ea03845c9f501ed1313e78de148cd3f6cad741a75d43a29b43da27f2e1e"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:10dffb601ccfb65262a27233ac273d552ddc4d8ae1bf93b21c94b8511bffe728"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:786902fb9ba7433aae840e0ed609f45c7bcd4e225ebb9c753aa39725bb3e6ad6"},
+    {file = "cffi-1.15.0-cp38-cp38-win32.whl", hash = "sha256:da5db4e883f1ce37f55c667e5c0de439df76ac4cb55964655906306918e7363c"},
+    {file = "cffi-1.15.0-cp38-cp38-win_amd64.whl", hash = "sha256:181dee03b1170ff1969489acf1c26533710231c58f95534e3edac87fff06c443"},
+    {file = "cffi-1.15.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:45e8636704eacc432a206ac7345a5d3d2c62d95a507ec70d62f23cd91770482a"},
+    {file = "cffi-1.15.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:31fb708d9d7c3f49a60f04cf5b119aeefe5644daba1cd2a0fe389b674fd1de37"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6dc2737a3674b3e344847c8686cf29e500584ccad76204efea14f451d4cc669a"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:74fdfdbfdc48d3f47148976f49fab3251e550a8720bebc99bf1483f5bfb5db3e"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffaa5c925128e29efbde7301d8ecaf35c8c60ffbcd6a1ffd3a552177c8e5e796"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3f7d084648d77af029acb79a0ff49a0ad7e9d09057a9bf46596dac9514dc07df"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ef1f279350da2c586a69d32fc8733092fd32cc8ac95139a00377841f59a3f8d8"},
+    {file = "cffi-1.15.0-cp39-cp39-win32.whl", hash = "sha256:2a23af14f408d53d5e6cd4e3d9a24ff9e05906ad574822a10563efcef137979a"},
+    {file = "cffi-1.15.0-cp39-cp39-win_amd64.whl", hash = "sha256:3773c4d81e6e818df2efbc7dd77325ca0dcb688116050fb2b3011218eda36139"},
+    {file = "cffi-1.15.0.tar.gz", hash = "sha256:920f0d66a896c2d99f0adbb391f990a84091179542c205fa53ce5787aff87954"},
+]
 cfgv = [
     {file = "cfgv-3.3.1-py2.py3-none-any.whl", hash = "sha256:c6a0883f3917a037485059700b9e75da2464e6c27051014ad85ba6aaa5884426"},
     {file = "cfgv-3.3.1.tar.gz", hash = "sha256:f5a830efb9ce7a445376bb66ec94c638a9787422f96264c98edc6bdeed8ab736"},
@@ -355,47 +464,47 @@ colorama = [
     {file = "colorama-0.4.4.tar.gz", hash = "sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b"},
 ]
 coverage = [
-    {file = "coverage-6.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:50ed480b798febce113709846b11f5d5ed1e529c88d8ae92f707806c50297abf"},
-    {file = "coverage-6.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:26f8f92699756cb7af2b30720de0c5bb8d028e923a95b6d0c891088025a1ac8f"},
-    {file = "coverage-6.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:60c2147921da7f4d2d04f570e1838db32b95c5509d248f3fe6417e91437eaf41"},
-    {file = "coverage-6.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:750e13834b597eeb8ae6e72aa58d1d831b96beec5ad1d04479ae3772373a8088"},
-    {file = "coverage-6.4-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:af5b9ee0fc146e907aa0f5fb858c3b3da9199d78b7bb2c9973d95550bd40f701"},
-    {file = "coverage-6.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:a022394996419142b33a0cf7274cb444c01d2bb123727c4bb0b9acabcb515dea"},
-    {file = "coverage-6.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:5a78cf2c43b13aa6b56003707c5203f28585944c277c1f3f109c7b041b16bd39"},
-    {file = "coverage-6.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9229d074e097f21dfe0643d9d0140ee7433814b3f0fc3706b4abffd1e3038632"},
-    {file = "coverage-6.4-cp310-cp310-win32.whl", hash = "sha256:fb45fe08e1abc64eb836d187b20a59172053999823f7f6ef4f18a819c44ba16f"},
-    {file = "coverage-6.4-cp310-cp310-win_amd64.whl", hash = "sha256:3cfd07c5889ddb96a401449109a8b97a165be9d67077df6802f59708bfb07720"},
-    {file = "coverage-6.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:03014a74023abaf5a591eeeaf1ac66a73d54eba178ff4cb1fa0c0a44aae70383"},
-    {file = "coverage-6.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c82f2cd69c71698152e943f4a5a6b83a3ab1db73b88f6e769fabc86074c3b08"},
-    {file = "coverage-6.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b546cf2b1974ddc2cb222a109b37c6ed1778b9be7e6b0c0bc0cf0438d9e45a6"},
-    {file = "coverage-6.4-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc173f1ce9ffb16b299f51c9ce53f66a62f4d975abe5640e976904066f3c835d"},
-    {file = "coverage-6.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c53ad261dfc8695062fc8811ac7c162bd6096a05a19f26097f411bdf5747aee7"},
-    {file = "coverage-6.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:eef5292b60b6de753d6e7f2d128d5841c7915fb1e3321c3a1fe6acfe76c38052"},
-    {file = "coverage-6.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:543e172ce4c0de533fa892034cce260467b213c0ea8e39da2f65f9a477425211"},
-    {file = "coverage-6.4-cp37-cp37m-win32.whl", hash = "sha256:00c8544510f3c98476bbd58201ac2b150ffbcce46a8c3e4fb89ebf01998f806a"},
-    {file = "coverage-6.4-cp37-cp37m-win_amd64.whl", hash = "sha256:b84ab65444dcc68d761e95d4d70f3cfd347ceca5a029f2ffec37d4f124f61311"},
-    {file = "coverage-6.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d548edacbf16a8276af13063a2b0669d58bbcfca7c55a255f84aac2870786a61"},
-    {file = "coverage-6.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:033ebec282793bd9eb988d0271c211e58442c31077976c19c442e24d827d356f"},
-    {file = "coverage-6.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:742fb8b43835078dd7496c3c25a1ec8d15351df49fb0037bffb4754291ef30ce"},
-    {file = "coverage-6.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d55fae115ef9f67934e9f1103c9ba826b4c690e4c5bcf94482b8b2398311bf9c"},
-    {file = "coverage-6.4-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5cd698341626f3c77784858427bad0cdd54a713115b423d22ac83a28303d1d95"},
-    {file = "coverage-6.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:62d382f7d77eeeaff14b30516b17bcbe80f645f5cf02bb755baac376591c653c"},
-    {file = "coverage-6.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:016d7f5cf1c8c84f533a3c1f8f36126fbe00b2ec0ccca47cc5731c3723d327c6"},
-    {file = "coverage-6.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:69432946f154c6add0e9ede03cc43b96e2ef2733110a77444823c053b1ff5166"},
-    {file = "coverage-6.4-cp38-cp38-win32.whl", hash = "sha256:83bd142cdec5e4a5c4ca1d4ff6fa807d28460f9db919f9f6a31babaaa8b88426"},
-    {file = "coverage-6.4-cp38-cp38-win_amd64.whl", hash = "sha256:4002f9e8c1f286e986fe96ec58742b93484195defc01d5cc7809b8f7acb5ece3"},
-    {file = "coverage-6.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e4f52c272fdc82e7c65ff3f17a7179bc5f710ebc8ce8a5cadac81215e8326740"},
-    {file = "coverage-6.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b5578efe4038be02d76c344007b13119b2b20acd009a88dde8adec2de4f630b5"},
-    {file = "coverage-6.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8099ea680201c2221f8468c372198ceba9338a5fec0e940111962b03b3f716a"},
-    {file = "coverage-6.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a00441f5ea4504f5abbc047589d09e0dc33eb447dc45a1a527c8b74bfdd32c65"},
-    {file = "coverage-6.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e76bd16f0e31bc2b07e0fb1379551fcd40daf8cdf7e24f31a29e442878a827c"},
-    {file = "coverage-6.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:8d2e80dd3438e93b19e1223a9850fa65425e77f2607a364b6fd134fcd52dc9df"},
-    {file = "coverage-6.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:341e9c2008c481c5c72d0e0dbf64980a4b2238631a7f9780b0fe2e95755fb018"},
-    {file = "coverage-6.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:21e6686a95025927775ac501e74f5940cdf6fe052292f3a3f7349b0abae6d00f"},
-    {file = "coverage-6.4-cp39-cp39-win32.whl", hash = "sha256:968ed5407f9460bd5a591cefd1388cc00a8f5099de9e76234655ae48cfdbe2c3"},
-    {file = "coverage-6.4-cp39-cp39-win_amd64.whl", hash = "sha256:e35217031e4b534b09f9b9a5841b9344a30a6357627761d4218818b865d45055"},
-    {file = "coverage-6.4-pp36.pp37.pp38-none-any.whl", hash = "sha256:e637ae0b7b481905358624ef2e81d7fb0b1af55f5ff99f9ba05442a444b11e45"},
-    {file = "coverage-6.4.tar.gz", hash = "sha256:727dafd7f67a6e1cad808dc884bd9c5a2f6ef1f8f6d2f22b37b96cb0080d4f49"},
+    {file = "coverage-6.4.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f1d5aa2703e1dab4ae6cf416eb0095304f49d004c39e9db1d86f57924f43006b"},
+    {file = "coverage-6.4.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4ce1b258493cbf8aec43e9b50d89982346b98e9ffdfaae8ae5793bc112fb0068"},
+    {file = "coverage-6.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c4e737f60c6936460c5be330d296dd5b48b3963f48634c53b3f7deb0f34ec4"},
+    {file = "coverage-6.4.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:84e65ef149028516c6d64461b95a8dbcfce95cfd5b9eb634320596173332ea84"},
+    {file = "coverage-6.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f69718750eaae75efe506406c490d6fc5a6161d047206cc63ce25527e8a3adad"},
+    {file = "coverage-6.4.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:e57816f8ffe46b1df8f12e1b348f06d164fd5219beba7d9433ba79608ef011cc"},
+    {file = "coverage-6.4.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:01c5615d13f3dd3aa8543afc069e5319cfa0c7d712f6e04b920431e5c564a749"},
+    {file = "coverage-6.4.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:75ab269400706fab15981fd4bd5080c56bd5cc07c3bccb86aab5e1d5a88dc8f4"},
+    {file = "coverage-6.4.1-cp310-cp310-win32.whl", hash = "sha256:a7f3049243783df2e6cc6deafc49ea123522b59f464831476d3d1448e30d72df"},
+    {file = "coverage-6.4.1-cp310-cp310-win_amd64.whl", hash = "sha256:ee2ddcac99b2d2aec413e36d7a429ae9ebcadf912946b13ffa88e7d4c9b712d6"},
+    {file = "coverage-6.4.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:fb73e0011b8793c053bfa85e53129ba5f0250fdc0392c1591fd35d915ec75c46"},
+    {file = "coverage-6.4.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:106c16dfe494de3193ec55cac9640dd039b66e196e4641fa8ac396181578b982"},
+    {file = "coverage-6.4.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:87f4f3df85aa39da00fd3ec4b5abeb7407e82b68c7c5ad181308b0e2526da5d4"},
+    {file = "coverage-6.4.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:961e2fb0680b4f5ad63234e0bf55dfb90d302740ae9c7ed0120677a94a1590cb"},
+    {file = "coverage-6.4.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:cec3a0f75c8f1031825e19cd86ee787e87cf03e4fd2865c79c057092e69e3a3b"},
+    {file = "coverage-6.4.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:129cd05ba6f0d08a766d942a9ed4b29283aff7b2cccf5b7ce279d50796860bb3"},
+    {file = "coverage-6.4.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:bf5601c33213d3cb19d17a796f8a14a9eaa5e87629a53979a5981e3e3ae166f6"},
+    {file = "coverage-6.4.1-cp37-cp37m-win32.whl", hash = "sha256:269eaa2c20a13a5bf17558d4dc91a8d078c4fa1872f25303dddcbba3a813085e"},
+    {file = "coverage-6.4.1-cp37-cp37m-win_amd64.whl", hash = "sha256:f02cbbf8119db68455b9d763f2f8737bb7db7e43720afa07d8eb1604e5c5ae28"},
+    {file = "coverage-6.4.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ffa9297c3a453fba4717d06df579af42ab9a28022444cae7fa605af4df612d54"},
+    {file = "coverage-6.4.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:145f296d00441ca703a659e8f3eb48ae39fb083baba2d7ce4482fb2723e050d9"},
+    {file = "coverage-6.4.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d44996140af8b84284e5e7d398e589574b376fb4de8ccd28d82ad8e3bea13"},
+    {file = "coverage-6.4.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2bd9a6fc18aab8d2e18f89b7ff91c0f34ff4d5e0ba0b33e989b3cd4194c81fd9"},
+    {file = "coverage-6.4.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3384f2a3652cef289e38100f2d037956194a837221edd520a7ee5b42d00cc605"},
+    {file = "coverage-6.4.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:9b3e07152b4563722be523e8cd0b209e0d1a373022cfbde395ebb6575bf6790d"},
+    {file = "coverage-6.4.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1480ff858b4113db2718848d7b2d1b75bc79895a9c22e76a221b9d8d62496428"},
+    {file = "coverage-6.4.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:865d69ae811a392f4d06bde506d531f6a28a00af36f5c8649684a9e5e4a85c83"},
+    {file = "coverage-6.4.1-cp38-cp38-win32.whl", hash = "sha256:664a47ce62fe4bef9e2d2c430306e1428ecea207ffd68649e3b942fa8ea83b0b"},
+    {file = "coverage-6.4.1-cp38-cp38-win_amd64.whl", hash = "sha256:26dff09fb0d82693ba9e6231248641d60ba606150d02ed45110f9ec26404ed1c"},
+    {file = "coverage-6.4.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d9c80df769f5ec05ad21ea34be7458d1dc51ff1fb4b2219e77fe24edf462d6df"},
+    {file = "coverage-6.4.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:39ee53946bf009788108b4dd2894bf1349b4e0ca18c2016ffa7d26ce46b8f10d"},
+    {file = "coverage-6.4.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f5b66caa62922531059bc5ac04f836860412f7f88d38a476eda0a6f11d4724f4"},
+    {file = "coverage-6.4.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fd180ed867e289964404051a958f7cccabdeed423f91a899829264bb7974d3d3"},
+    {file = "coverage-6.4.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:84631e81dd053e8a0d4967cedab6db94345f1c36107c71698f746cb2636c63e3"},
+    {file = "coverage-6.4.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:8c08da0bd238f2970230c2a0d28ff0e99961598cb2e810245d7fc5afcf1254e8"},
+    {file = "coverage-6.4.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:d42c549a8f41dc103a8004b9f0c433e2086add8a719da00e246e17cbe4056f72"},
+    {file = "coverage-6.4.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:309ce4a522ed5fca432af4ebe0f32b21d6d7ccbb0f5fcc99290e71feba67c264"},
+    {file = "coverage-6.4.1-cp39-cp39-win32.whl", hash = "sha256:fdb6f7bd51c2d1714cea40718f6149ad9be6a2ee7d93b19e9f00934c0f2a74d9"},
+    {file = "coverage-6.4.1-cp39-cp39-win_amd64.whl", hash = "sha256:342d4aefd1c3e7f620a13f4fe563154d808b69cccef415415aece4c786665397"},
+    {file = "coverage-6.4.1-pp36.pp37.pp38-none-any.whl", hash = "sha256:4803e7ccf93230accb928f3a68f00ffa80a88213af98ed338a57ad021ef06815"},
+    {file = "coverage-6.4.1.tar.gz", hash = "sha256:4321f075095a096e70aff1d002030ee612b65a205a0a0f5b815280d5dc58100c"},
 ]
 distlib = [
     {file = "distlib-0.3.4-py2.py3-none-any.whl", hash = "sha256:6564fe0a8f51e734df6333d08b8b94d4ea8ee6b99b5ed50613f731fd4089f34b"},
@@ -405,6 +514,21 @@ docutils = [
     {file = "docutils-0.18.1-py2.py3-none-any.whl", hash = "sha256:23010f129180089fbcd3bc08cfefccb3b890b0050e1ca00c867036e9d161b98c"},
     {file = "docutils-0.18.1.tar.gz", hash = "sha256:679987caf361a7539d76e584cbeddc311e3aee937877c87346f31debc63e9d06"},
 ]
+fastavro = [
+    {file = "fastavro-1.5.1-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:920d170560198741fa196a62a97c220173339766e6c14369c5c68bfe8cdafa25"},
+    {file = "fastavro-1.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b00b1711511981c4e2dd4a27ba5ae20897fe41ec7ab52eda868626d445081e5"},
+    {file = "fastavro-1.5.1-cp310-cp310-win_amd64.whl", hash = "sha256:04438b592980633ccf5d1de7798480a634ca581ae7575ab7671ba16773b6b428"},
+    {file = "fastavro-1.5.1-cp37-cp37m-macosx_10_15_x86_64.whl", hash = "sha256:0ab92ab744f9172da0791bfad0495d785c7c4f5a68924e3c6c6b39b78b044b11"},
+    {file = "fastavro-1.5.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:84ca1a60cecd710ead076585b56b954ab3e6e001d8e7384cb4ed20019b29e7a9"},
+    {file = "fastavro-1.5.1-cp37-cp37m-win_amd64.whl", hash = "sha256:b5ff657c0d48553492d8356a30b6112fcc6db69adce6bba31135272bc9d87d82"},
+    {file = "fastavro-1.5.1-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:0f1ed38042a2a90a7a5da170006459e73134f4c14f4fda9ebba99017adb1b14c"},
+    {file = "fastavro-1.5.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df83ebdd7b67b52a37bc84c6e25f7056f756fb216c5c8e5c95ae1673fcbb6015"},
+    {file = "fastavro-1.5.1-cp38-cp38-win_amd64.whl", hash = "sha256:0053347a92add6f448837ff00099b0a7200ec5dd58e173743d856d65d0574ddb"},
+    {file = "fastavro-1.5.1-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:6b4f8551ccbe0c9b19867b8c93029e8cfe8fa3757245caae6228f35ef0656371"},
+    {file = "fastavro-1.5.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ff241b5ce36df7af7461d001ca98fec6eacd56c4754c8ac7718e2d4b7b690a82"},
+    {file = "fastavro-1.5.1-cp39-cp39-win_amd64.whl", hash = "sha256:fb3491c88e7962a6b820548ddd12b9c0f6296ebd2385a3021296f14bfe35189a"},
+    {file = "fastavro-1.5.1.tar.gz", hash = "sha256:0815da740ced2261f90b0ddbb5bbe645e9c893c8f00e5dc8d30b8ec20f3c7fa9"},
+]
 filelock = [
     {file = "filelock-3.7.1-py3-none-any.whl", hash = "sha256:37def7b658813cda163b56fc564cdc75e86d338246458c4c28ae84cabefa2404"},
     {file = "filelock-3.7.1.tar.gz", hash = "sha256:3a0fd85166ad9dbab54c9aec96737b744106dc5f15c0b09a6744a445299fcf04"},
@@ -533,6 +657,10 @@ pyarrow = [
     {file = "pyarrow-8.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:cb06cacc19f3b426681f2f6803cc06ff481e7fe5b3a533b406bc5b2138843d4f"},
     {file = "pyarrow-8.0.0.tar.gz", hash = "sha256:4a18a211ed888f1ac0b0ebcb99e2d9a3e913a481120ee9b1fe33d3fedb945d4e"},
 ]
+pycparser = [
+    {file = "pycparser-2.21-py2.py3-none-any.whl", hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9"},
+    {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"},
+]
 pyparsing = [
     {file = "pyparsing-3.0.9-py3-none-any.whl", hash = "sha256:5026bae9a10eeaefb61dab2f09052b9f4307d44aee4eda64b309723d8d206bbc"},
     {file = "pyparsing-3.0.9.tar.gz", hash = "sha256:2b020ecf7d21b687f219b71ecad3631f644a47f01403fa1d1036b0c6416d70fb"},
@@ -545,6 +673,56 @@ pytest-checkdocs = [
     {file = "pytest-checkdocs-2.7.1.tar.gz", hash = "sha256:2b33b85eddfe5846a69bea4a759303e2d5a3be11d03bc7149f5ba1ef47e6c1ae"},
     {file = "pytest_checkdocs-2.7.1-py3-none-any.whl", hash = "sha256:294898c64c9ce1a178edc6660e48da23c7543bfd5a1cea7f0ca4c167745d8461"},
 ]
+python-snappy = [
+    {file = "python-snappy-0.6.1.tar.gz", hash = "sha256:b6a107ab06206acc5359d4c5632bd9b22d448702a79b3169b0c62e0fb808bb2a"},
+    {file = "python_snappy-0.6.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:b7f920eaf46ebf41bd26f9df51c160d40f9e00b7b48471c3438cb8d027f7fb9b"},
+    {file = "python_snappy-0.6.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4ec533a8c1f8df797bded662ec3e494d225b37855bb63eb0d75464a07947477c"},
+    {file = "python_snappy-0.6.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6f8bf4708a11b47517baf962f9a02196478bbb10fdb9582add4aa1459fa82380"},
+    {file = "python_snappy-0.6.1-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8d0c019ee7dcf2c60e240877107cddbd95a5b1081787579bf179938392d66480"},
+    {file = "python_snappy-0.6.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb18d9cd7b3f35a2f5af47bb8ed6a5bdbf4f3ddee37f3daade4ab7864c292f5b"},
+    {file = "python_snappy-0.6.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b265cde49774752aec9ca7f5d272e3f98718164afc85521622a8a5394158a2b5"},
+    {file = "python_snappy-0.6.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d017775851a778ec9cc32651c4464079d06d927303c2dde9ae9830ccf6fe94e1"},
+    {file = "python_snappy-0.6.1-cp310-cp310-win32.whl", hash = "sha256:8277d1f6282463c40761f802b742f833f9f2449fcdbb20a96579aa05c8feb614"},
+    {file = "python_snappy-0.6.1-cp310-cp310-win_amd64.whl", hash = "sha256:2aaaf618c68d8c9daebc23a20436bd01b09ee70d7fbf7072b7f38b06d2fab539"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:277757d5dad4e239dc1417438a0871b65b1b155beb108888e7438c27ffc6a8cc"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:e066a0586833d610c4bbddba0be5ba0e3e4f8e0bc5bb6d82103d8f8fc47bb59a"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:0d489b50f49433494160c45048fe806de6b3aeab0586e497ebd22a0bab56e427"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:463fd340a499d47b26ca42d2f36a639188738f6e2098c6dbf80aef0e60f461e1"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9837ac1650cc68d22a3cf5f15fb62c6964747d16cecc8b22431f113d6e39555d"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5e973e637112391f05581f427659c05b30b6843bc522a65be35ac7b18ce3dedd"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-win32.whl", hash = "sha256:c20498bd712b6e31a4402e1d027a1cd64f6a4a0066a3fe3c7344475886d07fdf"},
+    {file = "python_snappy-0.6.1-cp36-cp36m-win_amd64.whl", hash = "sha256:59e975be4206cc54d0a112ef72fa3970a57c2b1bcc2c97ed41d6df0ebe518228"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:2a7e528ab6e09c0d67dcb61a1730a292683e5ff9bb088950638d3170cf2a0a54"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:39692bedbe0b717001a99915ac0eb2d9d0bad546440d392a2042b96d813eede1"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:6a7620404da966f637b9ce8d4d3d543d363223f7a12452a575189c5355fc2d25"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7778c224efc38a40d274da4eb82a04cac27aae20012372a7db3c4bbd8926c4d4"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d029f7051ec1bbeaa3e03030b6d8ed47ceb69cae9016f493c802a08af54e026"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a0ad38bc98d0b0497a0b0dbc29409bcabfcecff4511ed7063403c86de16927bc"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-win32.whl", hash = "sha256:5a453c45178d7864c1bdd6bfe0ee3ed2883f63b9ba2c9bb967c6b586bf763f96"},
+    {file = "python_snappy-0.6.1-cp37-cp37m-win_amd64.whl", hash = "sha256:9f0c0d88b84259f93c3aa46398680646f2c23e43394779758d9f739c34e15295"},
+    {file = "python_snappy-0.6.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5bb05c28298803a74add08ba496879242ef159c75bc86a5406fac0ffc7dd021b"},
+    {file = "python_snappy-0.6.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9eac51307c6a1a38d5f86ebabc26a889fddf20cbba7a116ccb54ba1446601d5b"},
+    {file = "python_snappy-0.6.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:88b6ea78b83d2796f330b0af1b70cdd3965dbdab02d8ac293260ec2c8fe340ee"},
+    {file = "python_snappy-0.6.1-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8c07220408d3268e8268c9351c5c08041bc6f8c6172e59d398b71020df108541"},
+    {file = "python_snappy-0.6.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4038019b1bcaadde726a57430718394076c5a21545ebc5badad2c045a09546cf"},
+    {file = "python_snappy-0.6.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dc96668d9c7cc656609764275c5f8da58ef56d89bdd6810f6923d36497468ff7"},
+    {file = "python_snappy-0.6.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cf5bb9254e1c38aacf253d510d3d9be631bba21f3d068b17672b38b5cbf2fff5"},
+    {file = "python_snappy-0.6.1-cp38-cp38-win32.whl", hash = "sha256:eaf905a580f2747c4a474040a5063cd5e0cc3d1d2d6edb65f28196186493ad4a"},
+    {file = "python_snappy-0.6.1-cp38-cp38-win_amd64.whl", hash = "sha256:546c1a7470ecbf6239101e9aff0f709b68ca0f0268b34d9023019a55baa1f7c6"},
+    {file = "python_snappy-0.6.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:e3a013895c64352b49d0d8e107a84f99631b16dbab156ded33ebf0becf56c8b2"},
+    {file = "python_snappy-0.6.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3fb9a88a4dd6336488f3de67ce75816d0d796dce53c2c6e4d70e0b565633c7fd"},
+    {file = "python_snappy-0.6.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:735cd4528c55dbe4516d6d2b403331a99fc304f8feded8ae887cf97b67d589bb"},
+    {file = "python_snappy-0.6.1-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:90b0186516b7a101c14764b0c25931b741fb0102f21253eff67847b4742dfc72"},
+    {file = "python_snappy-0.6.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a993dc8aadd901915a510fe6af5f20ae4256f527040066c22a154db8946751f"},
+    {file = "python_snappy-0.6.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:530bfb9efebcc1aab8bb4ebcbd92b54477eed11f6cf499355e882970a6d3aa7d"},
+    {file = "python_snappy-0.6.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5843feb914796b1f0405ccf31ea0fb51034ceb65a7588edfd5a8250cb369e3b2"},
+    {file = "python_snappy-0.6.1-cp39-cp39-win32.whl", hash = "sha256:66c80e9b366012dbee262bb1869e4fc5ba8786cda85928481528bc4a72ec2ee8"},
+    {file = "python_snappy-0.6.1-cp39-cp39-win_amd64.whl", hash = "sha256:4d3cafdf454354a621c8ab7408e45aa4e9d5c0b943b61ff4815f71ca6bdf0130"},
+    {file = "python_snappy-0.6.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:586724a0276d7a6083a17259d0b51622e492289a9998848a1b01b6441ca12b2f"},
+    {file = "python_snappy-0.6.1-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:2be4f4550acd484912441f5f1209ba611ac399aac9355fee73611b9a0d4f949c"},
+    {file = "python_snappy-0.6.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0bdb6942180660bda7f7d01f4c0def3cfc72b1c6d99aad964801775a3e379aba"},
+    {file = "python_snappy-0.6.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:03bb511380fca2a13325b6f16fe8234c8e12da9660f0258cd45d9a02ffc916af"},
+]
 pyyaml = [
     {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"},
     {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"},
@@ -600,3 +778,49 @@ zipp = [
     {file = "zipp-3.8.0-py3-none-any.whl", hash = "sha256:c4f6e5bbf48e74f7a38e7cc5b0480ff42b0ae5178957d564d18932525d5cf099"},
     {file = "zipp-3.8.0.tar.gz", hash = "sha256:56bf8aadb83c24db6c4b577e13de374ccfb67da2078beba1d037c17980bf43ad"},
 ]
+zstandard = [
+    {file = "zstandard-0.17.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a1991cdf2e81e643b53fb8d272931d2bdf5f4e70d56a457e1ef95bde147ae627"},
+    {file = "zstandard-0.17.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4768449d8d1b0785309ace288e017cc5fa42e11a52bf08c90d9c3eb3a7a73cc6"},
+    {file = "zstandard-0.17.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b1ad6d2952b41d9a0ea702a474cc08c05210c6289e29dd496935c9ca3c7fb45c"},
+    {file = "zstandard-0.17.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90a9ba3a9c16b86afcb785b3c9418af39ccfb238fd5f6e429166e3ca8542b01f"},
+    {file = "zstandard-0.17.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:9cf18c156b3a108197a8bf90b37d03c31c8ef35a7c18807b321d96b74e12c301"},
+    {file = "zstandard-0.17.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c81fd9386449df0ebf1ab3e01187bb30d61122c74df53ba4880a2454d866e55d"},
+    {file = "zstandard-0.17.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:787efc741e61e00ffe5e65dac99b0dc5c88b9421012a207a91b869a8b1164921"},
+    {file = "zstandard-0.17.0-cp310-cp310-win32.whl", hash = "sha256:49cd09ccbd1e3c0e2690dd62ebf95064d84aa42b9db381867e0b138631f969f2"},
+    {file = "zstandard-0.17.0-cp310-cp310-win_amd64.whl", hash = "sha256:d78aac2ffc4e88ab1cbcad844669924c24e24c7c255de9628a18f14d832007c5"},
+    {file = "zstandard-0.17.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:c19d1e06569c277dcc872d80cbadf14a29e8199e013ff2a176d169f461439a40"},
+    {file = "zstandard-0.17.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d916018289d2f9a882e90d2e3bd41652861ce11b5ecd8515fa07ad31d97d56e5"},
+    {file = "zstandard-0.17.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f0c87f097d6867833a839b086eb8d03676bb87c2efa067a131099f04aa790683"},
+    {file = "zstandard-0.17.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:60943f71e3117583655a1eb76188a7cc78a25267ef09cc74be4d25a0b0c8b947"},
+    {file = "zstandard-0.17.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:208fa6bead577b2607205640078ee452e81fe20fe96321623c632bad9ebd7148"},
+    {file = "zstandard-0.17.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:42f3c02c7021073cafbc6cd152b288c56a25e585518861589bb08b063b6d2ad2"},
+    {file = "zstandard-0.17.0-cp36-cp36m-win32.whl", hash = "sha256:2a2ac752162ba5cbc869c60c4a4e54e890b2ee2ffb57d3ff159feab1ae4518db"},
+    {file = "zstandard-0.17.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d1405caa964ba11b2396bd9fd19940440217345752e192c936d084ba5fe67dcb"},
+    {file = "zstandard-0.17.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:ef62eb3bcfd6d786f439828bb544ebd3936432db669403e0b8f48e424f1d55f1"},
+    {file = "zstandard-0.17.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:477f172807a9fa83467b30d7c58876af1410d20177c554c27525211edf535bae"},
+    {file = "zstandard-0.17.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de1aa618306a741e0497878b7f845fd6c397e52dd096fb76ed791e7268887176"},
+    {file = "zstandard-0.17.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a827b9c464ee966524f8e82ec1aabb4a77ff9514cae041667fa81ae2ec8bd3e9"},
+    {file = "zstandard-0.17.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3cf96ace804945e53bc3e5294097e5fa32a2d43bc52416c632b414b870ee0a21"},
+    {file = "zstandard-0.17.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:802109f67328c5b822d4fdac28e1cf65a24de2e2e99d76cdbeee9121cedb1b6c"},
+    {file = "zstandard-0.17.0-cp37-cp37m-win32.whl", hash = "sha256:a628f20d019feb0f3a171c7a55cc4f75681f3b8c1bd7a5009165a487314887cd"},
+    {file = "zstandard-0.17.0-cp37-cp37m-win_amd64.whl", hash = "sha256:7d2e7abac41d2b4b18f03575aca860d2cb647c343e13c23d6c769106a3db2f6f"},
+    {file = "zstandard-0.17.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f502fe79757434292174b04db114f9e25c767b2d5ca9e759d118b22a66f445f8"},
+    {file = "zstandard-0.17.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e37c4e21f696d6bcdbbc7caf98dffa505d04c0053909b9db0a6e8ca3b935eb07"},
+    {file = "zstandard-0.17.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8fd386d0ec1f9343f1776391d9e60d4eedced0a0b0e625bb89b91f6d05f70e83"},
+    {file = "zstandard-0.17.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:91a228a077fc7cd8486c273788d4a006a37d060cb4293f471eb0325c3113af68"},
+    {file = "zstandard-0.17.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:59eadb9f347d40e8f7ef77caffd0c04a31e82c1df82fe2d2a688032429d750ac"},
+    {file = "zstandard-0.17.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a71809ec062c5b7acf286ba6d4484e6fe8130fc2b93c25e596bb34e7810c79b2"},
+    {file = "zstandard-0.17.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8aedd38d357f6d5e2facd88ce62b4976afdc29db57216a23f14a0cd0ca05a8a3"},
+    {file = "zstandard-0.17.0-cp38-cp38-win32.whl", hash = "sha256:bd842ae3dbb7cba88beb022161c819fa80ca7d0c5a4ddd209e7daae85d904e49"},
+    {file = "zstandard-0.17.0-cp38-cp38-win_amd64.whl", hash = "sha256:d0e9fec68e304fb35c559c44530213adbc7d5918bdab906a45a0f40cd56c4de2"},
+    {file = "zstandard-0.17.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9ec62a4c2dbb0a86ee5138c16ef133e59a23ac108f8d7ac97aeb61d410ce6857"},
+    {file = "zstandard-0.17.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d5373a56b90052f171c8634fedc53a6ac371e6c742606e9825772a394bdbd4b0"},
+    {file = "zstandard-0.17.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f2e3ea5e4d5ecf3faefd4a5294acb6af1f0578b0cdd75d6b4529c45deaa54d6f"},
+    {file = "zstandard-0.17.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7a3a1aa9528087f6f4c47f4ece2d5e6a160527821263fb8174ff36429233e093"},
+    {file = "zstandard-0.17.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:bdf691a205bc492956e6daef7a06fb38f8cbe8b2c1cb0386f35f4412c360c9e9"},
+    {file = "zstandard-0.17.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:db993a56e21d903893933887984ca9b0d274f2b1db7b3cf21ba129783953864f"},
+    {file = "zstandard-0.17.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:a7756a9446f83c81101f6c0a48c3bfd8d387a249933c57b0d095ca8b20541337"},
+    {file = "zstandard-0.17.0-cp39-cp39-win32.whl", hash = "sha256:37e50501baaa935f13a1820ab2114f74313b5cb4cfff8146acb8c5b18cdced2a"},
+    {file = "zstandard-0.17.0-cp39-cp39-win_amd64.whl", hash = "sha256:b4e671c4c0804cdf752be26f260058bb858fbdaaef1340af170635913ecca01e"},
+    {file = "zstandard-0.17.0.tar.gz", hash = "sha256:fa9194cb91441df7242aa3ddc4cb184be38876cb10dd973674887f334bafbfb6"},
+]
diff --git a/python/pyproject.toml b/python/pyproject.toml
index b845f8b01704..afeee351ce52 100644
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -43,10 +43,15 @@ mmh3 = "^3.0.0"
 
 pyarrow = { version = "^8.0.0", optional = true }
 
+zstandard = { version = "^0.17.0", optional = true }
+
+python-snappy = { version = "^0.6.1", optional = true }
+
 [tool.poetry.dev-dependencies]
 pytest = "^7.0.0"
 pytest-checkdocs = "^2.0.0"
 pre-commit = "^2.0.0"
+fastavro = "^1.5.1"
 coverage = { version = "^6.0.0", extras = ["toml"] }
 
 [build-system]
@@ -55,6 +60,8 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.extras]
 pyarrow = ["pyarrow"]
+snappy = ["python-snappy"]
+python-snappy = ["zstandard"]
 
 [tool.black]
 line-length = 130
@@ -79,5 +86,13 @@ warn_unreachable = true
 module = "mypy-pyarrow.*"
 ignore_missing_imports = true
 
+[[tool.mypy.overrides]]
+module = "mypy-snappy.*"
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = "mypy-zstandard.*"
+ignore_missing_imports = true
+
 [tool.coverage.run]
 source = ['src/']
diff --git a/python/spellcheck-dictionary.txt b/python/spellcheck-dictionary.txt
index 41da147758d2..8bb0b868c388 100644
--- a/python/spellcheck-dictionary.txt
+++ b/python/spellcheck-dictionary.txt
@@ -57,3 +57,9 @@ UnboundPredicate
 BoundPredicate
 BooleanExpression
 BooleanExpressionVisitor
+zigzag
+unix
+zlib
+Codecs
+codecs
+uri
diff --git a/python/src/iceberg/avro/__init__.py b/python/src/iceberg/avro/__init__.py
new file mode 100644
index 000000000000..13a83393a912
--- /dev/null
+++ b/python/src/iceberg/avro/__init__.py
@@ -0,0 +1,16 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
diff --git a/python/src/iceberg/avro/codecs/__init__.py b/python/src/iceberg/avro/codecs/__init__.py
new file mode 100644
index 000000000000..28dd23f83f9e
--- /dev/null
+++ b/python/src/iceberg/avro/codecs/__init__.py
@@ -0,0 +1,40 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""
+Contains Codecs for Python Avro.
+
+Note that the word "codecs" means "compression/decompression algorithms" in the
+Avro world (https://avro.apache.org/docs/current/spec.html#Object+Container+Files),
+so don't confuse it with the Python's "codecs", which is a package mainly for
+converting character sets (https://docs.python.org/3/library/codecs.html).
+"""
+from __future__ import annotations
+
+from iceberg.avro.codecs.bzip2 import BZip2Codec
+from iceberg.avro.codecs.codec import Codec
+from iceberg.avro.codecs.deflate import DeflateCodec
+from iceberg.avro.codecs.snappy_codec import SnappyCodec
+from iceberg.avro.codecs.zstandard_codec import ZStandardCodec
+
+KNOWN_CODECS: dict[str, type[Codec] | None] = {
+    "null": None,
+    "bzip2": BZip2Codec,
+    "snappy": SnappyCodec,
+    "zstandard": ZStandardCodec,
+    "deflate": DeflateCodec,
+}
diff --git a/python/src/iceberg/avro/codecs/bzip2.py b/python/src/iceberg/avro/codecs/bzip2.py
new file mode 100644
index 000000000000..b92c248de272
--- /dev/null
+++ b/python/src/iceberg/avro/codecs/bzip2.py
@@ -0,0 +1,43 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+from iceberg.avro.codecs.codec import Codec
+
+try:
+    import bz2
+
+    class BZip2Codec(Codec):
+        @staticmethod
+        def compress(data: bytes) -> tuple[bytes, int]:
+            compressed_data = bz2.compress(data)
+            return compressed_data, len(compressed_data)
+
+        @staticmethod
+        def decompress(data: bytes) -> bytes:
+            return bz2.decompress(data)
+
+except ImportError:
+
+    class BZip2Codec(Codec):  # type: ignore
+        @staticmethod
+        def compress(data: bytes) -> tuple[bytes, int]:
+            raise ImportError("Python bzip2 support not installed, please install the extension")
+
+        @staticmethod
+        def decompress(data: bytes) -> bytes:
+            raise ImportError("Python bzip2 support not installed, please install the extension")
diff --git a/python/src/iceberg/avro/codecs/codec.py b/python/src/iceberg/avro/codecs/codec.py
new file mode 100644
index 000000000000..1c04f0db3e20
--- /dev/null
+++ b/python/src/iceberg/avro/codecs/codec.py
@@ -0,0 +1,33 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class Codec(ABC):
+    """Abstract base class for all Avro codec classes."""
+
+    @staticmethod
+    @abstractmethod
+    def compress(data: bytes) -> tuple[bytes, int]:
+        ...
+
+    @staticmethod
+    @abstractmethod
+    def decompress(data: bytes) -> bytes:
+        ...
diff --git a/python/src/iceberg/avro/codecs/deflate.py b/python/src/iceberg/avro/codecs/deflate.py
new file mode 100644
index 000000000000..c1f8bf30b720
--- /dev/null
+++ b/python/src/iceberg/avro/codecs/deflate.py
@@ -0,0 +1,36 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+import zlib
+
+from iceberg.avro.codecs.codec import Codec
+
+
+class DeflateCodec(Codec):
+    @staticmethod
+    def compress(data: bytes) -> tuple[bytes, int]:
+        # The first two characters and last character are zlib
+        # wrappers around deflate data.
+        compressed_data = zlib.compress(data)[2:-1]
+        return compressed_data, len(compressed_data)
+
+    @staticmethod
+    def decompress(data: bytes) -> bytes:
+        # -15 is the log of the window size; negative indicates
+        # "raw" (no zlib headers) decompression.  See zlib.h.
+        return zlib.decompress(data, -15)
diff --git a/python/src/iceberg/avro/codecs/snappy_codec.py b/python/src/iceberg/avro/codecs/snappy_codec.py
new file mode 100644
index 000000000000..92b599cdface
--- /dev/null
+++ b/python/src/iceberg/avro/codecs/snappy_codec.py
@@ -0,0 +1,69 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+import binascii
+import struct
+
+from iceberg.avro.codecs.codec import Codec
+
+STRUCT_CRC32 = struct.Struct(">I")  # big-endian unsigned int
+
+try:
+    import snappy
+
+    class SnappyCodec(Codec):
+        @staticmethod
+        def _check_crc32(bytes_: bytes, checksum: bytes) -> None:
+            """Incrementally compute CRC-32 from bytes and compare to a checksum
+
+            Args:
+              bytes_ (bytes): The bytes to check against `checksum`
+              checksum (bytes): Byte representation of a checksum
+
+            Raises:
+              ValueError: If the computed CRC-32 does not match the checksum
+            """
+            if binascii.crc32(bytes_) & 0xFFFFFFFF != STRUCT_CRC32.unpack(checksum)[0]:
+                raise ValueError("Checksum failure")
+
+        @staticmethod
+        def compress(data: bytes) -> tuple[bytes, int]:
+            compressed_data = snappy.compress(data)
+            # A 4-byte, big-endian CRC32 checksum
+            compressed_data += STRUCT_CRC32.pack(binascii.crc32(data) & 0xFFFFFFFF)
+            return compressed_data, len(compressed_data)
+
+        @staticmethod
+        def decompress(data: bytes) -> bytes:
+            # Compressed data includes a 4-byte CRC32 checksum
+            data = data[0:-4]
+            uncompressed = snappy.decompress(data)
+            checksum = data[-4:]
+            SnappyCodec._check_crc32(uncompressed, checksum)
+            return uncompressed
+
+except ImportError:
+
+    class SnappyCodec(Codec):  # type: ignore
+        @staticmethod
+        def compress(data: bytes) -> tuple[bytes, int]:
+            raise ImportError("Snappy support not installed, please install using `pip install pyiceberg[snappy]`")
+
+        @staticmethod
+        def decompress(data: bytes) -> bytes:
+            raise ImportError("Snappy support not installed, please install using `pip install pyiceberg[snappy]`")
diff --git a/python/src/iceberg/avro/codecs/zstandard_codec.py b/python/src/iceberg/avro/codecs/zstandard_codec.py
new file mode 100644
index 000000000000..8144628b06c6
--- /dev/null
+++ b/python/src/iceberg/avro/codecs/zstandard_codec.py
@@ -0,0 +1,53 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+from io import BytesIO
+
+from iceberg.avro.codecs.codec import Codec
+
+try:
+    from zstandard import ZstdCompressor, ZstdDecompressor
+
+    class ZStandardCodec(Codec):
+        @staticmethod
+        def compress(data: bytes) -> tuple[bytes, int]:
+            compressed_data = ZstdCompressor().compress(data)
+            return compressed_data, len(compressed_data)
+
+        @staticmethod
+        def decompress(data: bytes) -> bytes:
+            uncompressed = bytearray()
+            dctx = ZstdDecompressor()
+            with dctx.stream_reader(BytesIO(data)) as reader:
+                while True:
+                    chunk = reader.read(16384)
+                    if not chunk:
+                        break
+                    uncompressed.extend(chunk)
+            return uncompressed
+
+except ImportError:
+
+    class ZStandardCodec(Codec):  # type: ignore
+        @staticmethod
+        def compress(data: bytes) -> tuple[bytes, int]:
+            raise ImportError("Zstandard support not installed, please install using `pip install pyiceberg[zstandard]`")
+
+        @staticmethod
+        def decompress(data: bytes) -> bytes:
+            raise ImportError("Zstandard support not installed, please install using `pip install pyiceberg[zstandard]`")
diff --git a/python/src/iceberg/avro/decoder.py b/python/src/iceberg/avro/decoder.py
new file mode 100644
index 000000000000..24312cdd250f
--- /dev/null
+++ b/python/src/iceberg/avro/decoder.py
@@ -0,0 +1,165 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+import decimal
+import struct
+from datetime import date, datetime, time
+
+from iceberg.io.base import InputStream
+from iceberg.utils.datetime import (
+    days_to_date,
+    micros_to_time,
+    micros_to_timestamp,
+    micros_to_timestamptz,
+)
+from iceberg.utils.decimal import unscaled_to_decimal
+
+STRUCT_FLOAT = struct.Struct("<f")  # little-endian float
+STRUCT_DOUBLE = struct.Struct("<d")  # little-endian double
+STRUCT_SIGNED_SHORT = struct.Struct(">h")  # big-endian signed short
+STRUCT_SIGNED_INT = struct.Struct(">i")  # big-endian signed int
+STRUCT_SIGNED_LONG = struct.Struct(">q")  # big-endian signed long
+
+
+class BinaryDecoder:
+    """Read leaf values."""
+
+    _input_stream: InputStream
+
+    def __init__(self, input_stream: InputStream) -> None:
+        """
+        reader is a Python object on which we can call read, seek, and tell.
+        """
+        self._input_stream = input_stream
+
+    def read(self, n: int) -> bytes:
+        """
+        Read n bytes.
+        """
+        if n < 0:
+            raise ValueError(f"Requested {n} bytes to read, expected positive integer.")
+        read_bytes = self._input_stream.read(n)
+        if len(read_bytes) != n:
+            raise ValueError(f"Read {len(read_bytes)} bytes, expected {n} bytes")
+        return read_bytes
+
+    def read_boolean(self) -> bool:
+        """
+        a boolean is written as a single byte
+        whose value is either 0 (false) or 1 (true).
+        """
+        return ord(self.read(1)) == 1
+
+    def read_int(self) -> int:
+        """int values are written using variable-length, zigzag coding."""
+        return self.read_long()
+
+    def read_long(self) -> int:
+        """long values are written using variable-length, zigzag coding."""
+        b = ord(self.read(1))
+        n = b & 0x7F
+        shift = 7
+        while (b & 0x80) != 0:
+            b = ord(self.read(1))
+            n |= (b & 0x7F) << shift
+            shift += 7
+        datum = (n >> 1) ^ -(n & 1)
+        return datum
+
+    def read_float(self) -> float:
+        """
+        A float is written as 4 bytes.
+        The float is converted into a 32-bit integer using a method equivalent to
+        Java's floatToIntBits and then encoded in little-endian format.
+        """
+        return float(STRUCT_FLOAT.unpack(self.read(4))[0])
+
+    def read_double(self) -> float:
+        """
+        A double is written as 8 bytes.
+        The double is converted into a 64-bit integer using a method equivalent to
+        Java's doubleToLongBits and then encoded in little-endian format.
+        """
+        return float(STRUCT_DOUBLE.unpack(self.read(8))[0])
+
+    def read_decimal_from_bytes(self, precision: int, scale: int) -> decimal.Decimal:
+        """
+        Decimal bytes are decoded as signed short, int or long depending on the
+        size of bytes.
+        """
+        size = self.read_long()
+        return self.read_decimal_from_fixed(precision, scale, size)
+
+    def read_decimal_from_fixed(self, precision: int, scale: int, size: int) -> decimal.Decimal:
+        """
+        Decimal is encoded as fixed. Fixed instances are encoded using the
+        number of bytes declared in the schema.
+        """
+        data = self.read(size)
+        unscaled_datum = int.from_bytes(data, byteorder="big", signed=True)
+        return unscaled_to_decimal(unscaled_datum, scale)
+
+    def read_bytes(self) -> bytes:
+        """
+        Bytes are encoded as a long followed by that many bytes of data.
+        """
+        return self.read(self.read_long())
+
+    def read_utf8(self) -> str:
+        """
+        A string is encoded as a long followed by
+        that many bytes of UTF-8 encoded character data.
+        """
+        return self.read_bytes().decode("utf-8")
+
+    def read_date_from_int(self) -> date:
+        """
+        int is decoded as python date object.
+        int stores the number of days from
+        the unix epoch, 1 January 1970 (ISO calendar).
+        """
+        return days_to_date(self.read_int())
+
+    def read_time_millis(self) -> time:
+        """
+        int is decoded as python time object which represents
+        the number of milliseconds after midnight, 00:00:00.000.
+        """
+        millis = self.read_int()
+        return micros_to_time(millis * 1000)
+
+    def read_time_micros(self) -> time:
+        """
+        long is decoded as python time object which represents
+        the number of microseconds after midnight, 00:00:00.000000.
+        """
+        return micros_to_time(self.read_long())
+
+    def read_timestamp_micros(self) -> datetime:
+        """
+        long is decoded as python datetime object which represents
+        the number of microseconds from the unix epoch, 1 January 1970.
+        """
+        return micros_to_timestamp(self.read_long())
+
+    def read_timestamptz_micros(self):
+        """
+        long is decoded as python datetime object which represents
+        the number of microseconds from the unix epoch, 1 January 1970.
+
+        Adjusted to UTC
+        """
+        return micros_to_timestamptz(self.read_long())
diff --git a/python/src/iceberg/avro/file.py b/python/src/iceberg/avro/file.py
new file mode 100644
index 000000000000..0eec227e9543
--- /dev/null
+++ b/python/src/iceberg/avro/file.py
@@ -0,0 +1,181 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+# pylint: disable=W0621
+"""
+Avro reader for reading Avro files
+"""
+from __future__ import annotations
+
+import json
+from dataclasses import dataclass
+from io import SEEK_SET
+
+from iceberg.avro.codecs import KNOWN_CODECS, Codec
+from iceberg.avro.decoder import BinaryDecoder
+from iceberg.avro.reader import AvroStruct, ConstructReader, StructReader
+from iceberg.io.base import InputFile, InputStream
+from iceberg.io.memory import MemoryInputStream
+from iceberg.schema import Schema, visit
+from iceberg.types import (
+    FixedType,
+    MapType,
+    NestedField,
+    StringType,
+    StructType,
+)
+from iceberg.utils.schema_conversion import AvroSchemaConversion
+
+VERSION = 1
+MAGIC = bytes(b"Obj" + bytearray([VERSION]))
+MAGIC_SIZE = len(MAGIC)
+SYNC_SIZE = 16
+META_SCHEMA = StructType(
+    NestedField(name="magic", field_id=100, field_type=FixedType(length=MAGIC_SIZE), required=True),
+    NestedField(
+        field_id=200,
+        name="meta",
+        field_type=MapType(key_id=201, key_type=StringType(), value_id=202, value_type=StringType(), value_required=True),
+        required=True,
+    ),
+    NestedField(field_id=300, name="sync", field_type=FixedType(length=SYNC_SIZE), required=True),
+)
+
+_CODEC_KEY = "avro.codec"
+_SCHEMA_KEY = "avro.schema"
+
+
+@dataclass(frozen=True)
+class AvroFileHeader:
+    magic: bytes
+    meta: dict[str, str]
+    sync: bytes
+
+    def compression_codec(self) -> type[Codec] | None:
+        """Get the file's compression codec algorithm from the file's metadata.
+
+        In the case of a null codec, we return a None indicating that we
+        don't need to compress/decompress
+        """
+        codec_name = self.meta.get(_CODEC_KEY, "null")
+        if codec_name not in KNOWN_CODECS:
+            raise ValueError(f"Unsupported codec: {codec_name}")
+
+        return KNOWN_CODECS[codec_name]
+
+    def get_schema(self) -> Schema:
+        if _SCHEMA_KEY in self.meta:
+            avro_schema_string = self.meta[_SCHEMA_KEY]
+            avro_schema = json.loads(avro_schema_string)
+            return AvroSchemaConversion().avro_to_iceberg(avro_schema)
+        else:
+            raise ValueError("No schema found in Avro file headers")
+
+
+@dataclass
+class Block:
+    reader: StructReader
+    block_records: int
+    block_decoder: BinaryDecoder
+    position: int = 0
+
+    def __iter__(self):
+        return self
+
+    def has_next(self) -> bool:
+        return self.position < self.block_records
+
+    def __next__(self) -> AvroStruct:
+        if self.has_next():
+            self.position += 1
+            return self.reader.read(self.block_decoder)
+        raise StopIteration
+
+
+class AvroFile:
+    input_file: InputFile
+    input_stream: InputStream
+    header: AvroFileHeader
+    schema: Schema
+    file_length: int
+    reader: StructReader
+
+    decoder: BinaryDecoder
+    block: Block | None = None
+
+    def __init__(self, input_file: InputFile) -> None:
+        self.input_file = input_file
+
+    def __enter__(self):
+        """
+        Opens the file and reads the header and generates
+        a reader tree to start reading the payload
+
+        Returns:
+            A generator returning the AvroStructs
+        """
+        self.input_stream = self.input_file.open()
+        self.decoder = BinaryDecoder(self.input_stream)
+        self.header = self._read_header()
+        self.schema = self.header.get_schema()
+        self.file_length = len(self.input_file)
+        self.reader = visit(self.schema, ConstructReader())
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        self.input_stream.close()
+
+    def __iter__(self) -> AvroFile:
+        return self
+
+    def _read_block(self) -> int:
+        # If there is already a block, we'll have the sync bytes
+        if self.block:
+            sync_marker = self.decoder.read(SYNC_SIZE)
+            if sync_marker != self.header.sync:
+                raise ValueError(f"Expected sync bytes {self.header.sync!r}, but got {sync_marker!r}")
+            if self.is_EOF():
+                raise StopIteration
+        block_records = self.decoder.read_long()
+
+        block_bytes_len = self.decoder.read_long()
+        block_bytes = self.decoder.read(block_bytes_len)
+        if codec := self.header.compression_codec():
+            block_bytes = codec.decompress(block_bytes)
+
+        self.block = Block(
+            reader=self.reader, block_records=block_records, block_decoder=BinaryDecoder(MemoryInputStream(block_bytes))
+        )
+        return block_records
+
+    def __next__(self) -> AvroStruct:
+        if self.block and self.block.has_next():
+            return next(self.block)
+
+        new_block = self._read_block()
+
+        if new_block > 0:
+            return self.__next__()
+        raise StopIteration
+
+    def _read_header(self) -> AvroFileHeader:
+        self.input_stream.seek(0, SEEK_SET)
+        reader = visit(META_SCHEMA, ConstructReader())
+        _header = reader.read(self.decoder)
+        return AvroFileHeader(magic=_header.get(0), meta=_header.get(1), sync=_header.get(2))
+
+    def is_EOF(self) -> bool:
+        return self.input_stream.tell() == self.file_length
diff --git a/python/src/iceberg/avro/reader.py b/python/src/iceberg/avro/reader.py
new file mode 100644
index 000000000000..bd8f1b4e8087
--- /dev/null
+++ b/python/src/iceberg/avro/reader.py
@@ -0,0 +1,316 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+"""
+Classes for building the Reader tree
+
+Constructing a reader tree from the schema makes it easy
+to decouple the reader implementation from the schema.
+
+The reader tree can be changed in such a way that the
+read schema is different, while respecting the read schema
+"""
+from __future__ import annotations
+
+from abc import abstractmethod
+from dataclasses import dataclass, field
+from datetime import date, datetime, time
+from decimal import Decimal
+from functools import singledispatch
+from typing import Any
+from uuid import UUID
+
+from iceberg.avro.decoder import BinaryDecoder
+from iceberg.files import StructProtocol
+from iceberg.schema import Schema, SchemaVisitor
+from iceberg.types import (
+    BinaryType,
+    BooleanType,
+    DateType,
+    DecimalType,
+    DoubleType,
+    FixedType,
+    FloatType,
+    IntegerType,
+    ListType,
+    LongType,
+    MapType,
+    NestedField,
+    PrimitiveType,
+    StringType,
+    StructType,
+    TimestampType,
+    TimestamptzType,
+    TimeType,
+)
+from iceberg.utils.singleton import Singleton
+
+
+@dataclass(frozen=True)
+class AvroStruct(StructProtocol):
+    _data: list[Any | StructProtocol] = field()
+
+    def set(self, pos: int, value: Any) -> None:
+        self._data[pos] = value
+
+    def get(self, pos: int) -> Any:
+        return self._data[pos]
+
+
+class Reader(Singleton):
+    @abstractmethod
+    def read(self, decoder: BinaryDecoder) -> Any:
+        ...
+
+
+class NoneReader(Reader):
+    def read(self, _: BinaryDecoder) -> None:
+        return None
+
+
+class BooleanReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> bool:
+        return decoder.read_boolean()
+
+
+class IntegerReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> int:
+        return decoder.read_int()
+
+
+class LongReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> int:
+        return decoder.read_long()
+
+
+class FloatReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> float:
+        return decoder.read_float()
+
+
+class DoubleReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> float:
+        return decoder.read_double()
+
+
+class DateReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> date:
+        return decoder.read_date_from_int()
+
+
+class TimeReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> time:
+        return decoder.read_time_micros()
+
+
+class TimestampReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> datetime:
+        return decoder.read_timestamp_micros()
+
+
+class TimestamptzReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> datetime:
+        return decoder.read_timestamptz_micros()
+
+
+class StringReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> str:
+        return decoder.read_utf8()
+
+
+class UUIDReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> UUID:
+        return UUID(decoder.read_utf8())
+
+
+@dataclass(frozen=True)
+class FixedReader(Reader):
+    length: int = field()
+
+    def read(self, decoder: BinaryDecoder) -> bytes:
+        return decoder.read(self.length)
+
+
+class BinaryReader(Reader):
+    def read(self, decoder: BinaryDecoder) -> bytes:
+        return decoder.read_bytes()
+
+
+@dataclass(frozen=True)
+class DecimalReader(Reader):
+    precision: int = field()
+    scale: int = field()
+
+    def read(self, decoder: BinaryDecoder) -> Decimal:
+        return decoder.read_decimal_from_bytes(self.precision, self.scale)
+
+
+@dataclass(frozen=True)
+class OptionReader(Reader):
+    option: Reader = field()
+
+    def read(self, decoder: BinaryDecoder) -> Any | None:
+        # For the Iceberg spec it is required to set the default value to null
+        # From https://iceberg.apache.org/spec/#avro
+        # Optional fields must always set the Avro field default value to null.
+        #
+        # This means that null has to come first:
+        # https://avro.apache.org/docs/current/spec.html
+        # type of the default value must match the first element of the union.
+        # This is enforced in the schema conversion, which happens prior
+        # to building the reader tree
+        if decoder.read_int() > 0:
+            return self.option.read(decoder)
+        return None
+
+
+@dataclass(frozen=True)
+class StructReader(Reader):
+    fields: tuple[Reader, ...] = field()
+
+    def read(self, decoder: BinaryDecoder) -> AvroStruct:
+        return AvroStruct([field.read(decoder) for field in self.fields])
+
+
+@dataclass(frozen=True)
+class ListReader(Reader):
+    element: Reader
+
+    def read(self, decoder: BinaryDecoder) -> list:
+        read_items = []
+        block_count = decoder.read_long()
+        while block_count != 0:
+            if block_count < 0:
+                block_count = -block_count
+                # We ignore the block size for now
+                _ = decoder.read_long()
+            for _ in range(block_count):
+                read_items.append(self.element.read(decoder))
+            block_count = decoder.read_long()
+        return read_items
+
+
+@dataclass(frozen=True)
+class MapReader(Reader):
+    key: Reader
+    value: Reader
+
+    def read(self, decoder: BinaryDecoder) -> dict:
+        read_items = {}
+        block_count = decoder.read_long()
+        while block_count != 0:
+            if block_count < 0:
+                block_count = -block_count
+                # We ignore the block size for now
+                _ = decoder.read_long()
+            for _ in range(block_count):
+                key = self.key.read(decoder)
+                read_items[key] = self.value.read(decoder)
+            block_count = decoder.read_long()
+
+        return read_items
+
+
+class ConstructReader(SchemaVisitor[Reader]):
+    def schema(self, schema: Schema, struct_result: Reader) -> Reader:
+        return struct_result
+
+    def struct(self, struct: StructType, field_results: list[Reader]) -> Reader:
+        return StructReader(tuple(field_results))
+
+    def field(self, field: NestedField, field_result: Reader) -> Reader:
+        return field_result if field.required else OptionReader(field_result)
+
+    def list(self, list_type: ListType, element_result: Reader) -> Reader:
+        element_reader = element_result if list_type.element_required else OptionReader(element_result)
+        return ListReader(element_reader)
+
+    def map(self, map_type: MapType, key_result: Reader, value_result: Reader) -> Reader:
+        value_reader = value_result if map_type.value_required else OptionReader(value_result)
+        return MapReader(key_result, value_reader)
+
+    def primitive(self, primitive: PrimitiveType) -> Reader:
+        return primitive_reader(primitive)
+
+
+@singledispatch
+def primitive_reader(primitive: PrimitiveType) -> Reader:
+    raise ValueError(f"Unknown type: {primitive}")
+
+
+@primitive_reader.register(FixedType)
+def _(primitive: FixedType) -> Reader:
+    return FixedReader(primitive.length)
+
+
+@primitive_reader.register(DecimalType)
+def _(primitive: DecimalType) -> Reader:
+    return DecimalReader(primitive.precision, primitive.scale)
+
+
+@primitive_reader.register(BooleanType)
+def _(_: BooleanType) -> Reader:
+    return BooleanReader()
+
+
+@primitive_reader.register(IntegerType)
+def _(_: IntegerType) -> Reader:
+    return IntegerReader()
+
+
+@primitive_reader.register(LongType)
+def _(_: LongType) -> Reader:
+    return LongReader()
+
+
+@primitive_reader.register(FloatType)
+def _(_: FloatType) -> Reader:
+    return FloatReader()
+
+
+@primitive_reader.register(DoubleType)
+def _(_: DoubleType) -> Reader:
+    return DoubleReader()
+
+
+@primitive_reader.register(DateType)
+def _(_: DateType) -> Reader:
+    return DateReader()
+
+
+@primitive_reader.register(TimeType)
+def _(_: TimeType) -> Reader:
+    return TimeReader()
+
+
+@primitive_reader.register(TimestampType)
+def _(_: TimestampType) -> Reader:
+    return TimestampReader()
+
+
+@primitive_reader.register(TimestamptzType)
+def _(_: TimestamptzType) -> Reader:
+    return TimestamptzReader()
+
+
+@primitive_reader.register(StringType)
+def _(_: StringType) -> Reader:
+    return StringReader()
+
+
+@primitive_reader.register(BinaryType)
+def _(_: StringType) -> Reader:
+    return BinaryReader()
diff --git a/python/src/iceberg/files.py b/python/src/iceberg/files.py
index 586aab498c08..e56009235797 100644
--- a/python/src/iceberg/files.py
+++ b/python/src/iceberg/files.py
@@ -45,5 +45,5 @@ def get(self, pos: int) -> Any:
         ...
 
     @abstractmethod
-    def set(self, pos: int, value) -> None:
+    def set(self, pos: int, value: Any) -> None:
         ...
diff --git a/python/src/iceberg/io/base.py b/python/src/iceberg/io/base.py
index 4e4ff30cdb26..458a3d591e3d 100644
--- a/python/src/iceberg/io/base.py
+++ b/python/src/iceberg/io/base.py
@@ -24,29 +24,35 @@
 """
 
 from abc import ABC, abstractmethod
+from io import SEEK_SET
 from typing import Protocol, Union, runtime_checkable
 
 
 @runtime_checkable
-class InputStream(Protocol):  # pragma: no cover
+class InputStream(Protocol):
     """A protocol for the file-like object returned by InputFile.open(...)
 
     This outlines the minimally required methods for a seekable input stream returned from an InputFile
     implementation's `open(...)` method. These methods are a subset of IOBase/RawIOBase.
     """
 
-    def read(self, size: int) -> bytes:
+    @abstractmethod
+    def read(self, size: int = 0) -> bytes:
         ...
 
-    def seek(self, offset: int, whence: int) -> None:
+    @abstractmethod
+    def seek(self, offset: int, whence: int = SEEK_SET) -> None:
         ...
 
+    @abstractmethod
     def tell(self) -> int:
         ...
 
+    @abstractmethod
     def closed(self) -> bool:
         ...
 
+    @abstractmethod
     def close(self) -> None:
         ...
 
@@ -59,12 +65,15 @@ class OutputStream(Protocol):  # pragma: no cover
     implementation's `create(...)` method. These methods are a subset of IOBase/RawIOBase.
     """
 
+    @abstractmethod
     def write(self, b: bytes) -> None:
         ...
 
+    @abstractmethod
     def closed(self) -> bool:
         ...
 
+    @abstractmethod
     def close(self) -> None:
         ...
 
diff --git a/python/src/iceberg/io/memory.py b/python/src/iceberg/io/memory.py
new file mode 100644
index 000000000000..0e9dcb9c99e4
--- /dev/null
+++ b/python/src/iceberg/io/memory.py
@@ -0,0 +1,75 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+from io import SEEK_CUR, SEEK_END, SEEK_SET
+
+from iceberg.io.base import InputStream
+
+
+class MemoryInputStream(InputStream):
+    """
+    Simple in memory stream that we use to store decompressed blocks
+
+    Examples:
+        >>> stream = MemoryInputStream(b'22memory1925')
+        >>> stream.tell()
+        0
+        >>> stream.read(2)
+        b'22'
+        >>> stream.tell()
+        2
+        >>> stream.seek(8)
+        >>> stream.read(4)
+        b'1925'
+        >>> stream.close()
+        >>> stream.closed()
+        True
+    """
+
+    buffer: bytes
+    len: int
+    pos: int
+
+    def __init__(self, buffer: bytes):
+        self.buffer = buffer
+        self.len = len(buffer)
+        self.pos = 0
+
+    def read(self, size: int = 0) -> bytes:
+        b = self.buffer[self.pos : self.pos + size]
+        self.pos += size
+        return b
+
+    def seek(self, offset: int, whence: int = SEEK_SET) -> None:
+        if whence == SEEK_SET:
+            self.pos = offset
+        elif whence == SEEK_CUR:
+            self.pos += offset
+        elif whence == SEEK_END:
+            self.pos = self.len + offset
+        else:
+            raise ValueError(f"Unknown whence {offset}")
+
+    def tell(self) -> int:
+        return self.pos
+
+    def closed(self) -> bool:
+        return not hasattr(self, "buffer")
+
+    def close(self) -> None:
+        del self.buffer
+        self.pos = 0
diff --git a/python/src/iceberg/types.py b/python/src/iceberg/types.py
index d665dbcae607..d3ae67237380 100644
--- a/python/src/iceberg/types.py
+++ b/python/src/iceberg/types.py
@@ -165,7 +165,7 @@ class StructType(IcebergType):
     def __init__(self, *fields: NestedField, **kwargs):  # pylint: disable=super-init-not-called
         if not fields and "fields" in kwargs:
             fields = kwargs["fields"]
-        object.__setattr__(self, "fields", fields)
+        object.__setattr__(self, "fields", tuple(fields))
 
     @cached_property
     def string_type(self) -> str:
diff --git a/python/src/iceberg/utils/datetime.py b/python/src/iceberg/utils/datetime.py
index c10dda4fb2bb..9e491ce9ce69 100644
--- a/python/src/iceberg/utils/datetime.py
+++ b/python/src/iceberg/utils/datetime.py
@@ -16,6 +16,8 @@
 #  under the License.
 """Helper methods for working with date/time representations
 """
+from __future__ import annotations
+
 import re
 from datetime import (
     date,
@@ -36,24 +38,31 @@ def micros_to_days(timestamp: int) -> int:
     return (datetime.fromtimestamp(timestamp / 1_000_000) - EPOCH_TIMESTAMP).days
 
 
+def micros_to_time(micros: int) -> time:
+    """Converts a timestamp in microseconds to a time"""
+    micros, microseconds = divmod(micros, 1000000)
+    micros, seconds = divmod(micros, 60)
+    micros, minutes = divmod(micros, 60)
+    hours = micros
+    return time(hour=hours, minute=minutes, second=seconds, microsecond=microseconds)
+
+
 def date_to_days(date_str: str) -> int:
     """Converts an ISO-8601 formatted date to days from 1970-01-01"""
     return (date.fromisoformat(date_str) - EPOCH_DATE).days
 
 
+def days_to_date(days: int) -> date:
+    """Creates a date from the number of days from 1970-01-01"""
+    return EPOCH_DATE + timedelta(days)
+
+
 def time_to_micros(time_str: str) -> int:
     """Converts an ISO-8601 formatted time to microseconds from midnight"""
     t = time.fromisoformat(time_str)
     return (((t.hour * 60 + t.minute) * 60) + t.second) * 1_000_000 + t.microsecond
 
 
-def time_from_micros(micros: int) -> time:
-    seconds = micros // 1_000_000
-    minutes = seconds // 60
-    hours = minutes // 60
-    return time(hour=hours, minute=minutes % 60, second=seconds % 60, microsecond=micros % 1_000_000)
-
-
 def datetime_to_micros(dt: datetime) -> int:
     """Converts a datetime to microseconds from 1970-01-01T00:00:00.000000"""
     if dt.tzinfo:
@@ -77,6 +86,18 @@ def timestamptz_to_micros(timestamptz_str: str) -> int:
     raise ValueError(f"Invalid timestamp with zone: {timestamptz_str} (must be ISO-8601)")
 
 
+def micros_to_timestamp(micros: int):
+    """Converts microseconds from epoch to a timestamp"""
+    dt = timedelta(microseconds=micros)
+    return EPOCH_TIMESTAMP + dt
+
+
+def micros_to_timestamptz(micros: int):
+    """Converts microseconds from epoch to an utc timestamp"""
+    dt = timedelta(microseconds=micros)
+    return EPOCH_TIMESTAMPTZ + dt
+
+
 def to_human_day(day_ordinal: int) -> str:
     """Converts a DateType value to human string"""
     return (EPOCH_DATE + timedelta(days=day_ordinal)).isoformat()
@@ -84,7 +105,7 @@ def to_human_day(day_ordinal: int) -> str:
 
 def to_human_time(micros_from_midnight: int) -> str:
     """Converts a TimeType value to human string"""
-    return time_from_micros(micros_from_midnight).isoformat()
+    return micros_to_time(micros_from_midnight).isoformat()
 
 
 def to_human_timestamptz(timestamp_micros: int) -> str:
diff --git a/python/src/iceberg/utils/schema_conversion.py b/python/src/iceberg/utils/schema_conversion.py
index 4e57daa0314e..f5b70354b9aa 100644
--- a/python/src/iceberg/utils/schema_conversion.py
+++ b/python/src/iceberg/utils/schema_conversion.py
@@ -14,9 +14,7 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-"""Utility class for converting between Avro and Iceberg schemas
-
-"""
+"""Utility class for converting between Avro and Iceberg schemas"""
 from __future__ import annotations
 
 import logging
@@ -116,23 +114,23 @@ def avro_to_iceberg(self, avro_schema: dict[str, Any]) -> Schema:
 
     def _resolve_union(self, type_union: dict | list | str) -> tuple[str | dict[str, Any], bool]:
         """
-        Converts Unions into their type and resolves if the field is optional
+        Converts Unions into their type and resolves if the field is required
 
         Examples:
             >>> AvroSchemaConversion()._resolve_union('str')
-            ('str', False)
-            >>> AvroSchemaConversion()._resolve_union(['null', 'str'])
             ('str', True)
+            >>> AvroSchemaConversion()._resolve_union(['null', 'str'])
+            ('str', False)
             >>> AvroSchemaConversion()._resolve_union([{'type': 'str'}])
-            ({'type': 'str'}, False)
-            >>> AvroSchemaConversion()._resolve_union(['null', {'type': 'str'}])
             ({'type': 'str'}, True)
+            >>> AvroSchemaConversion()._resolve_union(['null', {'type': 'str'}])
+            ({'type': 'str'}, False)
 
         Args:
             type_union: The field, can be a string 'str', list ['null', 'str'], or dict {"type": 'str'}
 
         Returns:
-            A tuple containing the type and nullability
+            A tuple containing the type and if required
 
         Raises:
             TypeError: In the case non-optional union types are encountered
@@ -140,20 +138,28 @@ def _resolve_union(self, type_union: dict | list | str) -> tuple[str | dict[str,
         avro_types: dict | list
         if isinstance(type_union, str):
             # It is a primitive and required
-            return type_union, False
+            return type_union, True
         elif isinstance(type_union, dict):
             # It is a context and required
-            return type_union, False
+            return type_union, True
         else:
             avro_types = type_union
 
-        is_optional = "null" in avro_types
-
         if len(avro_types) > 2:
-            raise TypeError("Non-optional types aren't part of the Iceberg specification")
+            raise TypeError(f"Non-optional types aren't part of the Iceberg specification: {avro_types}")
+
+        # For the Iceberg spec it is required to set the default value to null
+        # From https://iceberg.apache.org/spec/#avro
+        # Optional fields must always set the Avro field default value to null.
+        #
+        # This means that null has to come first:
+        # https://avro.apache.org/docs/current/spec.html
+        # type of the default value must match the first element of the union.
+        if "null" != avro_types[0]:
+            raise TypeError("Only null-unions are supported")
 
         # Filter the null value and return the type
-        return list(filter(lambda t: t != "null", avro_types))[0], is_optional
+        return list(filter(lambda t: t != "null", avro_types))[0], False
 
     def _convert_schema(self, avro_type: str | dict[str, Any]) -> IcebergType:
         """
@@ -205,13 +211,13 @@ def _convert_field(self, field: dict[str, Any]) -> NestedField:
         if "field-id" not in field:
             raise ValueError(f"Cannot convert field, missing field-id: {field}")
 
-        plain_type, is_optional = self._resolve_union(field["type"])
+        plain_type, required = self._resolve_union(field["type"])
 
         return NestedField(
             field_id=field["field-id"],
             name=field["name"],
             field_type=self._convert_schema(plain_type),
-            required=is_optional,
+            required=required,
             doc=field.get("doc"),
         )
 
@@ -273,12 +279,12 @@ def _convert_array_type(self, array_type: dict[str, Any]) -> ListType:
         if "element-id" not in array_type:
             raise ValueError(f"Cannot convert array-type, missing element-id: {array_type}")
 
-        plain_type, element_is_optional = self._resolve_union(array_type["items"])
+        plain_type, element_required = self._resolve_union(array_type["items"])
 
         return ListType(
             element_id=array_type["element-id"],
             element_type=self._convert_schema(plain_type),
-            element_required=element_is_optional,
+            element_required=element_required,
         )
 
     def _convert_map_type(self, map_type: dict[str, Any]) -> MapType:
@@ -290,7 +296,7 @@ def _convert_map_type(self, map_type: dict[str, Any]) -> MapType:
             >>> from iceberg.utils.schema_conversion import AvroSchemaConversion
             >>> avro_field = {
             ...     "type": "map",
-            ...     "values": ["long", "null"],
+            ...     "values": ["null", "long"],
             ...     "key-id": 101,
             ...     "value-id": 102,
             ... }
@@ -307,14 +313,14 @@ def _convert_map_type(self, map_type: dict[str, Any]) -> MapType:
 
         Returns: A MapType
         """
-        value_type, value_is_optional = self._resolve_union(map_type["values"])
+        value_type, value_required = self._resolve_union(map_type["values"])
         return MapType(
             key_id=map_type["key-id"],
             # Avro only supports string keys
             key_type=StringType(),
             value_id=map_type["value-id"],
             value_type=self._convert_schema(value_type),
-            value_required=value_is_optional,
+            value_required=value_required,
         )
 
     def _convert_logical_type(self, avro_logical_type: dict[str, Any]) -> IcebergType:
diff --git a/python/src/iceberg/utils/singleton.py b/python/src/iceberg/utils/singleton.py
index c36155de14e7..5643cdd1728f 100644
--- a/python/src/iceberg/utils/singleton.py
+++ b/python/src/iceberg/utils/singleton.py
@@ -14,7 +14,20 @@
 #  KIND, either express or implied.  See the License for the
 #  specific language governing permissions and limitations
 #  under the License.
+"""
+This is a singleton metaclass that can be used to cache and re-use existing objects
 
+In the Iceberg codebase we have a lot of objects that are stateless (for example Types such as StringType,
+BooleanType etc). FixedTypes have arguments (eg. Fixed[22]) that we also make part of the key when caching
+the newly created object.
+
+The Singleton uses a metaclass which essentially defines a new type. When the Type gets created, it will first
+evaluate the `__call__` method with all the arguments. If we already initialized a class earlier, we'll just
+return it.
+
+More information on metaclasses: https://docs.python.org/3/reference/datamodel.html#metaclasses
+
+"""
 from typing import ClassVar, Dict
 
 
diff --git a/python/tests/avro/__init__.py b/python/tests/avro/__init__.py
new file mode 100644
index 000000000000..a67d5ea255b2
--- /dev/null
+++ b/python/tests/avro/__init__.py
@@ -0,0 +1,16 @@
+#  Licensed to the Apache Software Foundation (ASF) under one
+#  or more contributor license agreements.  See the NOTICE file
+#  distributed with this work for additional information
+#  regarding copyright ownership.  The ASF licenses this file
+#  to you under the Apache License, Version 2.0 (the
+#  "License"); you may not use this file except in compliance
+#  with the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing,
+#  software distributed under the License is distributed on an
+#  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+#  KIND, either express or implied.  See the License for the
+#  specific language governing permissions and limitations
+#  under the License.
diff --git a/python/tests/avro/test_decoder.py b/python/tests/avro/test_decoder.py
new file mode 100644
index 000000000000..295715115183
--- /dev/null
+++ b/python/tests/avro/test_decoder.py
@@ -0,0 +1,140 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from datetime import date, datetime, timezone
+from decimal import Decimal
+from io import SEEK_SET
+
+import pytest
+
+from iceberg.avro.decoder import BinaryDecoder
+from iceberg.io.base import InputStream
+from iceberg.io.memory import MemoryInputStream
+
+
+def test_read_decimal_from_fixed():
+    mis = MemoryInputStream(b"\x00\x00\x00\x05\x6A\x48\x1C\xFB\x2C\x7C\x50\x00")
+    decoder = BinaryDecoder(mis)
+    actual = decoder.read_decimal_from_fixed(28, 15, 12)
+    expected = Decimal("99892.123400000000000")
+    assert actual == expected
+
+
+def test_read_long():
+    mis = MemoryInputStream(b"\x18")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_long() == 12
+
+
+def test_read_decimal():
+    mis = MemoryInputStream(b"\x18\x00\x00\x00\x05\x6A\x48\x1C\xFB\x2C\x7C\x50\x00")
+    decoder = BinaryDecoder(mis)
+    actual = decoder.read_decimal_from_bytes(28, 15)
+    expected = Decimal("99892.123400000000000")
+    assert actual == expected
+
+
+def test_decimal_from_fixed_big():
+    mis = MemoryInputStream(b"\x0E\xC2\x02\xE9\x06\x16\x33\x49\x77\x67\xA8\x00")
+    decoder = BinaryDecoder(mis)
+    actual = decoder.read_decimal_from_fixed(28, 15, 12)
+    expected = Decimal("4567335489766.998340000000000")
+    assert actual == expected
+
+
+def test_read_negative_bytes():
+    mis = MemoryInputStream(b"")
+    decoder = BinaryDecoder(mis)
+
+    with pytest.raises(ValueError) as exc_info:
+        decoder.read(-1)
+
+    assert "Requested -1 bytes to read, expected positive integer." in str(exc_info.value)
+
+
+class OneByteAtATimeInputStream(InputStream):
+    """
+    Fake input stream that just returns a single byte at the time
+    """
+
+    pos = 0
+
+    def read(self, size: int = 0) -> bytes:
+        self.pos += 1
+        return int.to_bytes(1, self.pos, byteorder="little")
+
+    def seek(self, offset: int, whence: int = SEEK_SET) -> None:
+        pass
+
+    def tell(self) -> int:
+        pass
+
+    def closed(self) -> bool:
+        pass
+
+    def close(self) -> None:
+        pass
+
+
+def test_read_single_byte_at_the_time():
+    decoder = BinaryDecoder(OneByteAtATimeInputStream())
+
+    with pytest.raises(ValueError) as exc_info:
+        decoder.read(2)
+
+    assert "Read 1 bytes, expected 2 bytes" in str(exc_info.value)
+
+
+def test_read_float():
+    mis = MemoryInputStream(b"\x00\x00\x9A\x41")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_float() == 19.25
+
+
+def test_read_double():
+    mis = MemoryInputStream(b"\x00\x00\x00\x00\x00\x40\x33\x40")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_double() == 19.25
+
+
+def test_read_date():
+    mis = MemoryInputStream(b"\xBC\x7D")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_date_from_int() == date(1991, 12, 27)
+
+
+def test_read_time_millis():
+    mis = MemoryInputStream(b"\xBC\x7D")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_time_millis().microsecond == 30000
+
+
+def test_read_time_micros():
+    mis = MemoryInputStream(b"\xBC\x7D")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_time_micros().microsecond == 8030
+
+
+def test_read_timestamp_micros():
+    mis = MemoryInputStream(b"\xBC\x7D")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_timestamp_micros() == datetime(1970, 1, 1, 0, 0, 0, 8030)
+
+
+def test_read_timestamptz_micros():
+    mis = MemoryInputStream(b"\xBC\x7D")
+    decoder = BinaryDecoder(mis)
+    assert decoder.read_timestamptz_micros() == datetime(1970, 1, 1, 0, 0, 0, 8030, tzinfo=timezone.utc)
diff --git a/python/tests/avro/test_file.py b/python/tests/avro/test_file.py
new file mode 100644
index 000000000000..d345865d118a
--- /dev/null
+++ b/python/tests/avro/test_file.py
@@ -0,0 +1,48 @@
+#  Licensed to the Apache Software Foundation (ASF) under one
+#  or more contributor license agreements.  See the NOTICE file
+#  distributed with this work for additional information
+#  regarding copyright ownership.  The ASF licenses this file
+#  to you under the Apache License, Version 2.0 (the
+#  "License"); you may not use this file except in compliance
+#  with the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing,
+#  software distributed under the License is distributed on an
+#  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+#  KIND, either express or implied.  See the License for the
+#  specific language governing permissions and limitations
+#  under the License.
+import pytest
+
+from iceberg.avro.codecs import DeflateCodec
+from iceberg.avro.file import AvroFileHeader
+
+
+def get_deflate_compressor():
+    header = AvroFileHeader(bytes(0), {"avro.codec": "deflate"}, bytes(16))
+    assert header.compression_codec() == DeflateCodec
+
+
+def get_null_compressor():
+    header = AvroFileHeader(bytes(0), {"avro.codec": "null"}, bytes(16))
+    assert header.compression_codec() is None
+
+
+def test_unknown_codec():
+    header = AvroFileHeader(bytes(0), {"avro.codec": "unknown"}, bytes(16))
+
+    with pytest.raises(ValueError) as exc_info:
+        header.compression_codec()
+
+    assert "Unsupported codec: unknown" in str(exc_info.value)
+
+
+def test_missing_schema():
+    header = AvroFileHeader(bytes(0), {}, bytes(16))
+
+    with pytest.raises(ValueError) as exc_info:
+        header.get_schema()
+
+    assert "No schema found in Avro file headers" in str(exc_info.value)
diff --git a/python/tests/avro/test_reader.py b/python/tests/avro/test_reader.py
new file mode 100644
index 000000000000..c310e69204cc
--- /dev/null
+++ b/python/tests/avro/test_reader.py
@@ -0,0 +1,455 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+import json
+
+import pytest
+
+from iceberg.avro.file import AvroFile
+from iceberg.avro.reader import (
+    AvroStruct,
+    BinaryReader,
+    BooleanReader,
+    DateReader,
+    DecimalReader,
+    DoubleReader,
+    FixedReader,
+    FloatReader,
+    IntegerReader,
+    LongReader,
+    StringReader,
+    TimeReader,
+    TimestampReader,
+    TimestamptzReader,
+    primitive_reader,
+)
+from iceberg.schema import Schema
+from iceberg.types import (
+    BinaryType,
+    BooleanType,
+    DateType,
+    DecimalType,
+    DoubleType,
+    FixedType,
+    FloatType,
+    IntegerType,
+    LongType,
+    PrimitiveType,
+    StringType,
+    TimestampType,
+    TimestamptzType,
+    TimeType,
+)
+from tests.io.test_io_base import LocalInputFile
+
+
+def test_read_header(generated_manifest_entry_file: str, iceberg_manifest_entry_schema: Schema):
+    with AvroFile(LocalInputFile(generated_manifest_entry_file)) as reader:
+        header = reader._read_header()
+
+    assert header.magic == b"Obj\x01"
+    assert json.loads(header.meta["avro.schema"]) == {
+        "type": "record",
+        "name": "manifest_entry",
+        "fields": [
+            {"field-id": 0, "name": "status", "type": "int"},
+            {"field-id": 1, "default": "null", "name": "snapshot_id", "type": ["null", "long"]},
+            {
+                "field-id": 2,
+                "name": "data_file",
+                "type": {
+                    "type": "record",
+                    "name": "r2",
+                    "fields": [
+                        {"field-id": 100, "doc": "Location URI with FS scheme", "name": "file_path", "type": "string"},
+                        {
+                            "field-id": 101,
+                            "doc": "File format name: avro, orc, or parquet",
+                            "name": "file_format",
+                            "type": "string",
+                        },
+                        {
+                            "field-id": 102,
+                            "name": "partition",
+                            "type": {
+                                "type": "record",
+                                "name": "r102",
+                                "fields": [{"field-id": 1000, "default": "null", "name": "VendorID", "type": ["null", "int"]}],
+                            },
+                        },
+                        {"field-id": 103, "doc": "Number of records in the file", "name": "record_count", "type": "long"},
+                        {"field-id": 104, "doc": "Total file size in bytes", "name": "file_size_in_bytes", "type": "long"},
+                        {"field-id": 105, "name": "block_size_in_bytes", "type": "long"},
+                        {
+                            "field-id": 108,
+                            "doc": "Map of column id to total size on disk",
+                            "default": "null",
+                            "name": "column_sizes",
+                            "type": [
+                                "null",
+                                {
+                                    "logicalType": "map",
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k117_v118",
+                                        "fields": [
+                                            {"field-id": 117, "name": "key", "type": "int"},
+                                            {"field-id": 118, "name": "value", "type": "long"},
+                                        ],
+                                    },
+                                },
+                            ],
+                        },
+                        {
+                            "field-id": 109,
+                            "doc": "Map of column id to total count, including null and NaN",
+                            "default": "null",
+                            "name": "value_counts",
+                            "type": [
+                                "null",
+                                {
+                                    "logicalType": "map",
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k119_v120",
+                                        "fields": [
+                                            {"field-id": 119, "name": "key", "type": "int"},
+                                            {"field-id": 120, "name": "value", "type": "long"},
+                                        ],
+                                    },
+                                },
+                            ],
+                        },
+                        {
+                            "field-id": 110,
+                            "doc": "Map of column id to null value count",
+                            "default": "null",
+                            "name": "null_value_counts",
+                            "type": [
+                                "null",
+                                {
+                                    "logicalType": "map",
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k121_v122",
+                                        "fields": [
+                                            {"field-id": 121, "name": "key", "type": "int"},
+                                            {"field-id": 122, "name": "value", "type": "long"},
+                                        ],
+                                    },
+                                },
+                            ],
+                        },
+                        {
+                            "field-id": 137,
+                            "doc": "Map of column id to number of NaN values in the column",
+                            "default": "null",
+                            "name": "nan_value_counts",
+                            "type": [
+                                "null",
+                                {
+                                    "logicalType": "map",
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k138_v139",
+                                        "fields": [
+                                            {"field-id": 138, "name": "key", "type": "int"},
+                                            {"field-id": 139, "name": "value", "type": "long"},
+                                        ],
+                                    },
+                                },
+                            ],
+                        },
+                        {
+                            "field-id": 125,
+                            "doc": "Map of column id to lower bound",
+                            "default": "null",
+                            "name": "lower_bounds",
+                            "type": [
+                                "null",
+                                {
+                                    "logicalType": "map",
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k126_v127",
+                                        "fields": [
+                                            {"field-id": 126, "name": "key", "type": "int"},
+                                            {"field-id": 127, "name": "value", "type": "bytes"},
+                                        ],
+                                    },
+                                },
+                            ],
+                        },
+                        {
+                            "field-id": 128,
+                            "doc": "Map of column id to upper bound",
+                            "default": "null",
+                            "name": "upper_bounds",
+                            "type": [
+                                "null",
+                                {
+                                    "logicalType": "map",
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k129_v130",
+                                        "fields": [
+                                            {"field-id": 129, "name": "key", "type": "int"},
+                                            {"field-id": 130, "name": "value", "type": "bytes"},
+                                        ],
+                                    },
+                                },
+                            ],
+                        },
+                        {
+                            "field-id": 131,
+                            "doc": "Encryption key metadata blob",
+                            "default": "null",
+                            "name": "key_metadata",
+                            "type": ["null", "bytes"],
+                        },
+                        {
+                            "field-id": 132,
+                            "doc": "Splittable offsets",
+                            "default": "null",
+                            "name": "split_offsets",
+                            "type": ["null", {"element-id": 133, "type": "array", "items": "long"}],
+                        },
+                        {
+                            "field-id": 140,
+                            "doc": "Sort order ID",
+                            "default": "null",
+                            "name": "sort_order_id",
+                            "type": ["null", "int"],
+                        },
+                    ],
+                },
+            },
+        ],
+    }
+
+    assert header.get_schema() == iceberg_manifest_entry_schema
+
+
+def test_read_manifest_entry_file(generated_manifest_entry_file: str):
+    with AvroFile(LocalInputFile(generated_manifest_entry_file)) as reader:
+        # Consume the generator
+        records = list(reader)
+
+    assert len(records) == 2, f"Expected 2 records, got {len(records)}"
+    assert records[0] == AvroStruct(
+        _data=[
+            1,
+            8744736658442914487,
+            AvroStruct(
+                _data=[
+                    "/home/iceberg/warehouse/nyc/taxis_partitioned/data/VendorID=null/00000-633-d8a4223e-dc97-45a1-86e1-adaba6e8abd7-00001.parquet",
+                    "PARQUET",
+                    AvroStruct(_data=[None]),
+                    19513,
+                    388872,
+                    67108864,
+                    {
+                        1: 53,
+                        2: 98153,
+                        3: 98693,
+                        4: 53,
+                        5: 53,
+                        6: 53,
+                        7: 17425,
+                        8: 18528,
+                        9: 53,
+                        10: 44788,
+                        11: 35571,
+                        12: 53,
+                        13: 1243,
+                        14: 2355,
+                        15: 12750,
+                        16: 4029,
+                        17: 110,
+                        18: 47194,
+                        19: 2948,
+                    },
+                    {
+                        1: 19513,
+                        2: 19513,
+                        3: 19513,
+                        4: 19513,
+                        5: 19513,
+                        6: 19513,
+                        7: 19513,
+                        8: 19513,
+                        9: 19513,
+                        10: 19513,
+                        11: 19513,
+                        12: 19513,
+                        13: 19513,
+                        14: 19513,
+                        15: 19513,
+                        16: 19513,
+                        17: 19513,
+                        18: 19513,
+                        19: 19513,
+                    },
+                    {
+                        1: 19513,
+                        2: 0,
+                        3: 0,
+                        4: 19513,
+                        5: 19513,
+                        6: 19513,
+                        7: 0,
+                        8: 0,
+                        9: 19513,
+                        10: 0,
+                        11: 0,
+                        12: 19513,
+                        13: 0,
+                        14: 0,
+                        15: 0,
+                        16: 0,
+                        17: 0,
+                        18: 0,
+                        19: 0,
+                    },
+                    {16: 0, 17: 0, 18: 0, 19: 0, 10: 0, 11: 0, 12: 0, 13: 0, 14: 0, 15: 0},
+                    {
+                        2: b"2020-04-01 00:00",
+                        3: b"2020-04-01 00:12",
+                        7: b"\x03\x00\x00\x00",
+                        8: b"\x01\x00\x00\x00",
+                        10: b"\xf6(\\\x8f\xc2\x05S\xc0",
+                        11: b"\x00\x00\x00\x00\x00\x00\x00\x00",
+                        13: b"\x00\x00\x00\x00\x00\x00\x00\x00",
+                        14: b"\x00\x00\x00\x00\x00\x00\xe0\xbf",
+                        15: b")\\\x8f\xc2\xf5(\x08\xc0",
+                        16: b"\x00\x00\x00\x00\x00\x00\x00\x00",
+                        17: b"\x00\x00\x00\x00\x00\x00\x00\x00",
+                        18: b"\xf6(\\\x8f\xc2\xc5S\xc0",
+                        19: b"\x00\x00\x00\x00\x00\x00\x04\xc0",
+                    },
+                    {
+                        2: b"2020-04-30 23:5:",
+                        3: b"2020-05-01 00:41",
+                        7: b"\t\x01\x00\x00",
+                        8: b"\t\x01\x00\x00",
+                        10: b"\xcd\xcc\xcc\xcc\xcc,_@",
+                        11: b"\x1f\x85\xebQ\\\xe2\xfe@",
+                        13: b"\x00\x00\x00\x00\x00\x00\x12@",
+                        14: b"\x00\x00\x00\x00\x00\x00\xe0?",
+                        15: b"q=\n\xd7\xa3\xf01@",
+                        16: b"\x00\x00\x00\x00\x00`B@",
+                        17: b"333333\xd3?",
+                        18: b"\x00\x00\x00\x00\x00\x18b@",
+                        19: b"\x00\x00\x00\x00\x00\x00\x04@",
+                    },
+                    None,
+                    [4],
+                    0,
+                ]
+            ),
+        ]
+    )
+
+
+def test_read_manifest_file_file(generated_manifest_file_file: str):
+    with AvroFile(LocalInputFile(generated_manifest_file_file)) as reader:
+        # Consume the generator
+        records = list(reader)
+
+    assert len(records) == 1, f"Expected 1 records, got {len(records)}"
+    assert records[0] == AvroStruct(
+        _data=[
+            "/home/iceberg/warehouse/nyc/taxis_partitioned/metadata/0125c686-8aa6-4502-bdcc-b6d17ca41a3b-m0.avro",
+            7989,
+            0,
+            9182715666859759686,
+            3,
+            0,
+            0,
+            [AvroStruct(_data=[True, False, b"\x01\x00\x00\x00", b"\x02\x00\x00\x00"])],
+            237993,
+            0,
+            0,
+        ]
+    )
+
+
+def test_fixed_reader():
+    assert primitive_reader(FixedType(22)) == FixedReader(22)
+
+
+def test_decimal_reader():
+    assert primitive_reader(DecimalType(19, 25)) == DecimalReader(19, 25)
+
+
+def test_boolean_reader():
+    assert primitive_reader(BooleanType()) == BooleanReader()
+
+
+def test_integer_reader():
+    assert primitive_reader(IntegerType()) == IntegerReader()
+
+
+def test_long_reader():
+    assert primitive_reader(LongType()) == LongReader()
+
+
+def test_float_reader():
+    assert primitive_reader(FloatType()) == FloatReader()
+
+
+def test_double_reader():
+    assert primitive_reader(DoubleType()) == DoubleReader()
+
+
+def test_date_reader():
+    assert primitive_reader(DateType()) == DateReader()
+
+
+def test_time_reader():
+    assert primitive_reader(TimeType()) == TimeReader()
+
+
+def test_timestamp_reader():
+    assert primitive_reader(TimestampType()) == TimestampReader()
+
+
+def test_timestamptz_reader():
+    assert primitive_reader(TimestamptzType()) == TimestamptzReader()
+
+
+def test_string_reader():
+    assert primitive_reader(StringType()) == StringReader()
+
+
+def test_binary_reader():
+    assert primitive_reader(BinaryType()) == BinaryReader()
+
+
+def test_unknown_type():
+    class UnknownType(PrimitiveType):
+        ...
+
+    with pytest.raises(ValueError) as exc_info:
+        primitive_reader(UnknownType())
+
+    assert "Unknown type:" in str(exc_info.value)
diff --git a/python/tests/conftest.py b/python/tests/conftest.py
index b5dd18b8d80a..48f3bf02390b 100644
--- a/python/tests/conftest.py
+++ b/python/tests/conftest.py
@@ -15,16 +15,20 @@
 # specific language governing permissions and limitations
 # under the License.
 
+from tempfile import TemporaryDirectory
 from typing import Any, Dict
 
 import pytest
 
 from iceberg import schema
+from iceberg.schema import Schema
 from iceberg.types import (
+    BinaryType,
     BooleanType,
     FloatType,
     IntegerType,
     ListType,
+    LongType,
     MapType,
     NestedField,
     StringType,
@@ -114,7 +118,367 @@ def foo_struct():
 
 
 @pytest.fixture(scope="session")
-def manifest_schema() -> Dict[str, Any]:
+def all_avro_types() -> Dict[str, Any]:
+    return {
+        "type": "record",
+        "name": "all_avro_types",
+        "fields": [
+            {"name": "primitive_string", "type": "string", "field-id": 100},
+            {"name": "primitive_int", "type": "int", "field-id": 200},
+            {"name": "primitive_long", "type": "long", "field-id": 300},
+            {"name": "primitive_float", "type": "float", "field-id": 400},
+            {"name": "primitive_double", "type": "double", "field-id": 500},
+            {"name": "primitive_bytes", "type": "bytes", "field-id": 600},
+            {
+                "type": "record",
+                "name": "Person",
+                "fields": [
+                    {"name": "name", "type": "string", "field-id": 701},
+                    {"name": "age", "type": "long", "field-id": 702},
+                    {"name": "gender", "type": ["string", "null"], "field-id": 703},
+                ],
+                "field-id": 700,
+            },
+            {
+                "name": "array_with_string",
+                "type": {
+                    "type": "array",
+                    "items": "string",
+                    "default": [],
+                    "element-id": 801,
+                },
+                "field-id": 800,
+            },
+            {
+                "name": "array_with_optional_string",
+                "type": [
+                    "null",
+                    {
+                        "type": "array",
+                        "items": ["string", "null"],
+                        "default": [],
+                        "element-id": 901,
+                    },
+                ],
+                "field-id": 900,
+            },
+            {
+                "name": "array_with_optional_record",
+                "type": [
+                    "null",
+                    {
+                        "type": "array",
+                        "items": [
+                            "null",
+                            {
+                                "type": "record",
+                                "name": "person",
+                                "fields": [
+                                    {"name": "name", "type": "string", "field-id": 1002},
+                                    {"name": "age", "type": "long", "field-id": 1003},
+                                    {"name": "gender", "type": ["string", "null"], "field-id": 1004},
+                                ],
+                            },
+                        ],
+                        "element-id": 1001,
+                    },
+                ],
+                "field-id": 1000,
+            },
+            {
+                "name": "map_with_longs",
+                "type": {
+                    "type": "map",
+                    "values": "long",
+                    "default": {},
+                    "key-id": 1101,
+                    "value-id": 1102,
+                },
+                "field-id": 1000,
+            },
+        ],
+    }
+
+
+@pytest.fixture
+def catalog() -> InMemoryCatalog:
+    return InMemoryCatalog("test.in.memory.catalog", {"test.key": "test.value"})
+
+
+manifest_entry_records = [
+    {
+        "status": 1,
+        "snapshot_id": 8744736658442914487,
+        "data_file": {
+            "file_path": "/home/iceberg/warehouse/nyc/taxis_partitioned/data/VendorID=null/00000-633-d8a4223e-dc97-45a1-86e1-adaba6e8abd7-00001.parquet",
+            "file_format": "PARQUET",
+            "partition": {"VendorID": None},
+            "record_count": 19513,
+            "file_size_in_bytes": 388872,
+            "block_size_in_bytes": 67108864,
+            "column_sizes": [
+                {"key": 1, "value": 53},
+                {"key": 2, "value": 98153},
+                {"key": 3, "value": 98693},
+                {"key": 4, "value": 53},
+                {"key": 5, "value": 53},
+                {"key": 6, "value": 53},
+                {"key": 7, "value": 17425},
+                {"key": 8, "value": 18528},
+                {"key": 9, "value": 53},
+                {"key": 10, "value": 44788},
+                {"key": 11, "value": 35571},
+                {"key": 12, "value": 53},
+                {"key": 13, "value": 1243},
+                {"key": 14, "value": 2355},
+                {"key": 15, "value": 12750},
+                {"key": 16, "value": 4029},
+                {"key": 17, "value": 110},
+                {"key": 18, "value": 47194},
+                {"key": 19, "value": 2948},
+            ],
+            "value_counts": [
+                {"key": 1, "value": 19513},
+                {"key": 2, "value": 19513},
+                {"key": 3, "value": 19513},
+                {"key": 4, "value": 19513},
+                {"key": 5, "value": 19513},
+                {"key": 6, "value": 19513},
+                {"key": 7, "value": 19513},
+                {"key": 8, "value": 19513},
+                {"key": 9, "value": 19513},
+                {"key": 10, "value": 19513},
+                {"key": 11, "value": 19513},
+                {"key": 12, "value": 19513},
+                {"key": 13, "value": 19513},
+                {"key": 14, "value": 19513},
+                {"key": 15, "value": 19513},
+                {"key": 16, "value": 19513},
+                {"key": 17, "value": 19513},
+                {"key": 18, "value": 19513},
+                {"key": 19, "value": 19513},
+            ],
+            "null_value_counts": [
+                {"key": 1, "value": 19513},
+                {"key": 2, "value": 0},
+                {"key": 3, "value": 0},
+                {"key": 4, "value": 19513},
+                {"key": 5, "value": 19513},
+                {"key": 6, "value": 19513},
+                {"key": 7, "value": 0},
+                {"key": 8, "value": 0},
+                {"key": 9, "value": 19513},
+                {"key": 10, "value": 0},
+                {"key": 11, "value": 0},
+                {"key": 12, "value": 19513},
+                {"key": 13, "value": 0},
+                {"key": 14, "value": 0},
+                {"key": 15, "value": 0},
+                {"key": 16, "value": 0},
+                {"key": 17, "value": 0},
+                {"key": 18, "value": 0},
+                {"key": 19, "value": 0},
+            ],
+            "nan_value_counts": [
+                {"key": 16, "value": 0},
+                {"key": 17, "value": 0},
+                {"key": 18, "value": 0},
+                {"key": 19, "value": 0},
+                {"key": 10, "value": 0},
+                {"key": 11, "value": 0},
+                {"key": 12, "value": 0},
+                {"key": 13, "value": 0},
+                {"key": 14, "value": 0},
+                {"key": 15, "value": 0},
+            ],
+            "lower_bounds": [
+                {"key": 2, "value": b"2020-04-01 00:00"},
+                {"key": 3, "value": b"2020-04-01 00:12"},
+                {"key": 7, "value": b"\x03\x00\x00\x00"},
+                {"key": 8, "value": b"\x01\x00\x00\x00"},
+                {"key": 10, "value": b"\xf6(\\\x8f\xc2\x05S\xc0"},
+                {"key": 11, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 13, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 14, "value": b"\x00\x00\x00\x00\x00\x00\xe0\xbf"},
+                {"key": 15, "value": b")\\\x8f\xc2\xf5(\x08\xc0"},
+                {"key": 16, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 17, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 18, "value": b"\xf6(\\\x8f\xc2\xc5S\xc0"},
+                {"key": 19, "value": b"\x00\x00\x00\x00\x00\x00\x04\xc0"},
+            ],
+            "upper_bounds": [
+                {"key": 2, "value": b"2020-04-30 23:5:"},
+                {"key": 3, "value": b"2020-05-01 00:41"},
+                {"key": 7, "value": b"\t\x01\x00\x00"},
+                {"key": 8, "value": b"\t\x01\x00\x00"},
+                {"key": 10, "value": b"\xcd\xcc\xcc\xcc\xcc,_@"},
+                {"key": 11, "value": b"\x1f\x85\xebQ\\\xe2\xfe@"},
+                {"key": 13, "value": b"\x00\x00\x00\x00\x00\x00\x12@"},
+                {"key": 14, "value": b"\x00\x00\x00\x00\x00\x00\xe0?"},
+                {"key": 15, "value": b"q=\n\xd7\xa3\xf01@"},
+                {"key": 16, "value": b"\x00\x00\x00\x00\x00`B@"},
+                {"key": 17, "value": b"333333\xd3?"},
+                {"key": 18, "value": b"\x00\x00\x00\x00\x00\x18b@"},
+                {"key": 19, "value": b"\x00\x00\x00\x00\x00\x00\x04@"},
+            ],
+            "key_metadata": None,
+            "split_offsets": [4],
+            "sort_order_id": 0,
+        },
+    },
+    {
+        "status": 1,
+        "snapshot_id": 8744736658442914487,
+        "data_file": {
+            "file_path": "/home/iceberg/warehouse/nyc/taxis_partitioned/data/VendorID=1/00000-633-d8a4223e-dc97-45a1-86e1-adaba6e8abd7-00002.parquet",
+            "file_format": "PARQUET",
+            "partition": {"VendorID": 1},
+            "record_count": 95050,
+            "file_size_in_bytes": 1265950,
+            "block_size_in_bytes": 67108864,
+            "column_sizes": [
+                {"key": 1, "value": 318},
+                {"key": 2, "value": 329806},
+                {"key": 3, "value": 331632},
+                {"key": 4, "value": 15343},
+                {"key": 5, "value": 2351},
+                {"key": 6, "value": 3389},
+                {"key": 7, "value": 71269},
+                {"key": 8, "value": 76429},
+                {"key": 9, "value": 16383},
+                {"key": 10, "value": 86992},
+                {"key": 11, "value": 89608},
+                {"key": 12, "value": 265},
+                {"key": 13, "value": 19377},
+                {"key": 14, "value": 1692},
+                {"key": 15, "value": 76162},
+                {"key": 16, "value": 4354},
+                {"key": 17, "value": 759},
+                {"key": 18, "value": 120650},
+                {"key": 19, "value": 11804},
+            ],
+            "value_counts": [
+                {"key": 1, "value": 95050},
+                {"key": 2, "value": 95050},
+                {"key": 3, "value": 95050},
+                {"key": 4, "value": 95050},
+                {"key": 5, "value": 95050},
+                {"key": 6, "value": 95050},
+                {"key": 7, "value": 95050},
+                {"key": 8, "value": 95050},
+                {"key": 9, "value": 95050},
+                {"key": 10, "value": 95050},
+                {"key": 11, "value": 95050},
+                {"key": 12, "value": 95050},
+                {"key": 13, "value": 95050},
+                {"key": 14, "value": 95050},
+                {"key": 15, "value": 95050},
+                {"key": 16, "value": 95050},
+                {"key": 17, "value": 95050},
+                {"key": 18, "value": 95050},
+                {"key": 19, "value": 95050},
+            ],
+            "null_value_counts": [
+                {"key": 1, "value": 0},
+                {"key": 2, "value": 0},
+                {"key": 3, "value": 0},
+                {"key": 4, "value": 0},
+                {"key": 5, "value": 0},
+                {"key": 6, "value": 0},
+                {"key": 7, "value": 0},
+                {"key": 8, "value": 0},
+                {"key": 9, "value": 0},
+                {"key": 10, "value": 0},
+                {"key": 11, "value": 0},
+                {"key": 12, "value": 95050},
+                {"key": 13, "value": 0},
+                {"key": 14, "value": 0},
+                {"key": 15, "value": 0},
+                {"key": 16, "value": 0},
+                {"key": 17, "value": 0},
+                {"key": 18, "value": 0},
+                {"key": 19, "value": 0},
+            ],
+            "nan_value_counts": [
+                {"key": 16, "value": 0},
+                {"key": 17, "value": 0},
+                {"key": 18, "value": 0},
+                {"key": 19, "value": 0},
+                {"key": 10, "value": 0},
+                {"key": 11, "value": 0},
+                {"key": 12, "value": 0},
+                {"key": 13, "value": 0},
+                {"key": 14, "value": 0},
+                {"key": 15, "value": 0},
+            ],
+            "lower_bounds": [
+                {"key": 1, "value": b"\x01\x00\x00\x00"},
+                {"key": 2, "value": b"2020-04-01 00:00"},
+                {"key": 3, "value": b"2020-04-01 00:03"},
+                {"key": 4, "value": b"\x00\x00\x00\x00"},
+                {"key": 5, "value": b"\x01\x00\x00\x00"},
+                {"key": 6, "value": b"N"},
+                {"key": 7, "value": b"\x01\x00\x00\x00"},
+                {"key": 8, "value": b"\x01\x00\x00\x00"},
+                {"key": 9, "value": b"\x01\x00\x00\x00"},
+                {"key": 10, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 11, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 13, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 14, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 15, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 16, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 17, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 18, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+                {"key": 19, "value": b"\x00\x00\x00\x00\x00\x00\x00\x00"},
+            ],
+            "upper_bounds": [
+                {"key": 1, "value": b"\x01\x00\x00\x00"},
+                {"key": 2, "value": b"2020-04-30 23:5:"},
+                {"key": 3, "value": b"2020-05-01 00:1:"},
+                {"key": 4, "value": b"\x06\x00\x00\x00"},
+                {"key": 5, "value": b"c\x00\x00\x00"},
+                {"key": 6, "value": b"Y"},
+                {"key": 7, "value": b"\t\x01\x00\x00"},
+                {"key": 8, "value": b"\t\x01\x00\x00"},
+                {"key": 9, "value": b"\x04\x00\x00\x00"},
+                {"key": 10, "value": b"\\\x8f\xc2\xf5(8\x8c@"},
+                {"key": 11, "value": b"\xcd\xcc\xcc\xcc\xcc,f@"},
+                {"key": 13, "value": b"\x00\x00\x00\x00\x00\x00\x1c@"},
+                {"key": 14, "value": b"\x9a\x99\x99\x99\x99\x99\xf1?"},
+                {"key": 15, "value": b"\x00\x00\x00\x00\x00\x00Y@"},
+                {"key": 16, "value": b"\x00\x00\x00\x00\x00\xb0X@"},
+                {"key": 17, "value": b"333333\xd3?"},
+                {"key": 18, "value": b"\xc3\xf5(\\\x8f:\x8c@"},
+                {"key": 19, "value": b"\x00\x00\x00\x00\x00\x00\x04@"},
+            ],
+            "key_metadata": None,
+            "split_offsets": [4],
+            "sort_order_id": 0,
+        },
+    },
+]
+
+manifest_file_records = [
+    {
+        "manifest_path": "/home/iceberg/warehouse/nyc/taxis_partitioned/metadata/0125c686-8aa6-4502-bdcc-b6d17ca41a3b-m0.avro",
+        "manifest_length": 7989,
+        "partition_spec_id": 0,
+        "added_snapshot_id": 9182715666859759686,
+        "added_data_files_count": 3,
+        "existing_data_files_count": 0,
+        "deleted_data_files_count": 0,
+        "partitions": [
+            {"contains_null": True, "contains_nan": False, "lower_bound": b"\x01\x00\x00\x00", "upper_bound": b"\x02\x00\x00\x00"}
+        ],
+        "added_rows_count": 237993,
+        "existing_rows_count": 0,
+        "deleted_rows_count": 0,
+    }
+]
+
+
+@pytest.fixture(scope="session")
+def avro_schema_manifest_file() -> Dict[str, Any]:
     return {
         "type": "record",
         "name": "manifest_file",
@@ -126,28 +490,28 @@ def manifest_schema() -> Dict[str, Any]:
                 "name": "added_snapshot_id",
                 "type": ["null", "long"],
                 "doc": "Snapshot ID that added the manifest",
-                "default": None,
+                "default": "null",
                 "field-id": 503,
             },
             {
                 "name": "added_data_files_count",
                 "type": ["null", "int"],
                 "doc": "Added entry count",
-                "default": None,
+                "default": "null",
                 "field-id": 504,
             },
             {
                 "name": "existing_data_files_count",
                 "type": ["null", "int"],
                 "doc": "Existing entry count",
-                "default": None,
+                "default": "null",
                 "field-id": 505,
             },
             {
                 "name": "deleted_data_files_count",
                 "type": ["null", "int"],
                 "doc": "Deleted entry count",
-                "default": None,
+                "default": "null",
                 "field-id": 506,
             },
             {
@@ -170,21 +534,21 @@ def manifest_schema() -> Dict[str, Any]:
                                     "name": "contains_nan",
                                     "type": ["null", "boolean"],
                                     "doc": "True if any file has a nan partition value",
-                                    "default": None,
+                                    "default": "null",
                                     "field-id": 518,
                                 },
                                 {
                                     "name": "lower_bound",
                                     "type": ["null", "bytes"],
                                     "doc": "Partition lower bound for all files",
-                                    "default": None,
+                                    "default": "null",
                                     "field-id": 510,
                                 },
                                 {
                                     "name": "upper_bound",
                                     "type": ["null", "bytes"],
                                     "doc": "Partition upper bound for all files",
-                                    "default": None,
+                                    "default": "null",
                                     "field-id": 511,
                                 },
                             ],
@@ -193,22 +557,22 @@ def manifest_schema() -> Dict[str, Any]:
                     },
                 ],
                 "doc": "Summary for each partition",
-                "default": None,
+                "default": "null",
                 "field-id": 507,
             },
-            {"name": "added_rows_count", "type": ["null", "long"], "doc": "Added rows count", "default": None, "field-id": 512},
+            {"name": "added_rows_count", "type": ["null", "long"], "doc": "Added rows count", "default": "null", "field-id": 512},
             {
                 "name": "existing_rows_count",
                 "type": ["null", "long"],
                 "doc": "Existing rows count",
-                "default": None,
+                "default": "null",
                 "field-id": 513,
             },
             {
                 "name": "deleted_rows_count",
                 "type": ["null", "long"],
                 "doc": "Deleted rows count",
-                "default": None,
+                "default": "null",
                 "field-id": 514,
             },
         ],
@@ -216,88 +580,381 @@ def manifest_schema() -> Dict[str, Any]:
 
 
 @pytest.fixture(scope="session")
-def all_avro_types() -> Dict[str, Any]:
+def avro_schema_manifest_entry() -> Dict[str, Any]:
     return {
         "type": "record",
-        "name": "all_avro_types",
+        "name": "manifest_entry",
         "fields": [
-            {"name": "primitive_string", "type": "string", "field-id": 100},
-            {"name": "primitive_int", "type": "int", "field-id": 200},
-            {"name": "primitive_long", "type": "long", "field-id": 300},
-            {"name": "primitive_float", "type": "float", "field-id": 400},
-            {"name": "primitive_double", "type": "double", "field-id": 500},
-            {"name": "primitive_bytes", "type": "bytes", "field-id": 600},
-            {
-                "type": "record",
-                "name": "Person",
-                "fields": [
-                    {"name": "name", "type": "string", "field-id": 701},
-                    {"name": "age", "type": "long", "field-id": 702},
-                    {"name": "gender", "type": ["string", "null"], "field-id": 703},
-                ],
-                "field-id": 700,
-            },
+            {"name": "status", "type": "int", "field-id": 0},
+            {"name": "snapshot_id", "type": ["null", "long"], "default": "null", "field-id": 1},
             {
-                "name": "array_with_string",
+                "name": "data_file",
                 "type": {
-                    "type": "array",
-                    "items": "string",
-                    "default": [],
-                    "element-id": 801,
-                },
-                "field-id": 800,
-            },
-            {
-                "name": "array_with_optional_string",
-                "type": [
-                    "null",
-                    {
-                        "type": "array",
-                        "items": ["string", "null"],
-                        "default": [],
-                        "element-id": 901,
-                    },
-                ],
-                "field-id": 900,
-            },
-            {
-                "name": "array_with_optional_record",
-                "type": [
-                    "null",
-                    {
-                        "type": "array",
-                        "items": [
-                            "null",
-                            {
+                    "type": "record",
+                    "name": "r2",
+                    "fields": [
+                        {"name": "file_path", "type": "string", "doc": "Location URI with FS scheme", "field-id": 100},
+                        {
+                            "name": "file_format",
+                            "type": "string",
+                            "doc": "File format name: avro, orc, or parquet",
+                            "field-id": 101,
+                        },
+                        {
+                            "name": "partition",
+                            "type": {
                                 "type": "record",
-                                "name": "person",
-                                "fields": [
-                                    {"name": "name", "type": "string", "field-id": 1002},
-                                    {"name": "age", "type": "long", "field-id": 1003},
-                                    {"name": "gender", "type": ["string", "null"], "field-id": 1004},
-                                ],
+                                "name": "r102",
+                                "fields": [{"name": "VendorID", "type": ["null", "int"], "default": "null", "field-id": 1000}],
                             },
-                        ],
-                        "element-id": 1001,
-                    },
-                ],
-                "field-id": 1000,
-            },
-            {
-                "name": "map_with_longs",
-                "type": {
-                    "type": "map",
-                    "values": "long",
-                    "default": {},
-                    "key-id": 1101,
-                    "value-id": 1102,
+                            "field-id": 102,
+                        },
+                        {"name": "record_count", "type": "long", "doc": "Number of records in the file", "field-id": 103},
+                        {"name": "file_size_in_bytes", "type": "long", "doc": "Total file size in bytes", "field-id": 104},
+                        {"name": "block_size_in_bytes", "type": "long", "field-id": 105},
+                        {
+                            "name": "column_sizes",
+                            "type": [
+                                "null",
+                                {
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k117_v118",
+                                        "fields": [
+                                            {"name": "key", "type": "int", "field-id": 117},
+                                            {"name": "value", "type": "long", "field-id": 118},
+                                        ],
+                                    },
+                                    "logicalType": "map",
+                                },
+                            ],
+                            "doc": "Map of column id to total size on disk",
+                            "default": "null",
+                            "field-id": 108,
+                        },
+                        {
+                            "name": "value_counts",
+                            "type": [
+                                "null",
+                                {
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k119_v120",
+                                        "fields": [
+                                            {"name": "key", "type": "int", "field-id": 119},
+                                            {"name": "value", "type": "long", "field-id": 120},
+                                        ],
+                                    },
+                                    "logicalType": "map",
+                                },
+                            ],
+                            "doc": "Map of column id to total count, including null and NaN",
+                            "default": "null",
+                            "field-id": 109,
+                        },
+                        {
+                            "name": "null_value_counts",
+                            "type": [
+                                "null",
+                                {
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k121_v122",
+                                        "fields": [
+                                            {"name": "key", "type": "int", "field-id": 121},
+                                            {"name": "value", "type": "long", "field-id": 122},
+                                        ],
+                                    },
+                                    "logicalType": "map",
+                                },
+                            ],
+                            "doc": "Map of column id to null value count",
+                            "default": "null",
+                            "field-id": 110,
+                        },
+                        {
+                            "name": "nan_value_counts",
+                            "type": [
+                                "null",
+                                {
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k138_v139",
+                                        "fields": [
+                                            {"name": "key", "type": "int", "field-id": 138},
+                                            {"name": "value", "type": "long", "field-id": 139},
+                                        ],
+                                    },
+                                    "logicalType": "map",
+                                },
+                            ],
+                            "doc": "Map of column id to number of NaN values in the column",
+                            "default": "null",
+                            "field-id": 137,
+                        },
+                        {
+                            "name": "lower_bounds",
+                            "type": [
+                                "null",
+                                {
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k126_v127",
+                                        "fields": [
+                                            {"name": "key", "type": "int", "field-id": 126},
+                                            {"name": "value", "type": "bytes", "field-id": 127},
+                                        ],
+                                    },
+                                    "logicalType": "map",
+                                },
+                            ],
+                            "doc": "Map of column id to lower bound",
+                            "default": "null",
+                            "field-id": 125,
+                        },
+                        {
+                            "name": "upper_bounds",
+                            "type": [
+                                "null",
+                                {
+                                    "type": "array",
+                                    "items": {
+                                        "type": "record",
+                                        "name": "k129_v130",
+                                        "fields": [
+                                            {"name": "key", "type": "int", "field-id": 129},
+                                            {"name": "value", "type": "bytes", "field-id": 130},
+                                        ],
+                                    },
+                                    "logicalType": "map",
+                                },
+                            ],
+                            "doc": "Map of column id to upper bound",
+                            "default": "null",
+                            "field-id": 128,
+                        },
+                        {
+                            "name": "key_metadata",
+                            "type": ["null", "bytes"],
+                            "doc": "Encryption key metadata blob",
+                            "default": "null",
+                            "field-id": 131,
+                        },
+                        {
+                            "name": "split_offsets",
+                            "type": ["null", {"type": "array", "items": "long", "element-id": 133}],
+                            "doc": "Splittable offsets",
+                            "default": "null",
+                            "field-id": 132,
+                        },
+                        {
+                            "name": "sort_order_id",
+                            "type": ["null", "int"],
+                            "doc": "Sort order ID",
+                            "default": "null",
+                            "field-id": 140,
+                        },
+                    ],
                 },
-                "field-id": 1000,
+                "field-id": 2,
             },
         ],
     }
 
 
-@pytest.fixture
-def catalog() -> InMemoryCatalog:
-    return InMemoryCatalog("test.in.memory.catalog", {"test.key": "test.value"})
+@pytest.fixture(scope="session")
+def generated_manifest_entry_file(avro_schema_manifest_entry):
+    from fastavro import parse_schema, writer
+
+    parsed_schema = parse_schema(avro_schema_manifest_entry)
+
+    with TemporaryDirectory() as tmpdir:
+        tmp_avro_file = tmpdir + "/manifest.avro"
+        with open(tmp_avro_file, "wb") as out:
+            writer(out, parsed_schema, manifest_entry_records)
+        yield tmp_avro_file
+
+
+@pytest.fixture(scope="session")
+def generated_manifest_file_file(avro_schema_manifest_file):
+    from fastavro import parse_schema, writer
+
+    parsed_schema = parse_schema(avro_schema_manifest_file)
+
+    with TemporaryDirectory() as tmpdir:
+        tmp_avro_file = tmpdir + "/manifest.avro"
+        with open(tmp_avro_file, "wb") as out:
+            writer(out, parsed_schema, manifest_file_records)
+        yield tmp_avro_file
+
+
+@pytest.fixture(scope="session")
+def iceberg_manifest_entry_schema() -> Schema:
+    return Schema(
+        NestedField(field_id=0, name="status", field_type=IntegerType(), required=True),
+        NestedField(field_id=1, name="snapshot_id", field_type=LongType(), required=False),
+        NestedField(
+            field_id=2,
+            name="data_file",
+            field_type=StructType(
+                NestedField(
+                    field_id=100,
+                    name="file_path",
+                    field_type=StringType(),
+                    doc="Location URI with FS scheme",
+                    required=True,
+                ),
+                NestedField(
+                    field_id=101,
+                    name="file_format",
+                    field_type=StringType(),
+                    doc="File format name: avro, orc, or parquet",
+                    required=True,
+                ),
+                NestedField(
+                    field_id=102,
+                    name="partition",
+                    field_type=StructType(
+                        NestedField(
+                            field_id=1000,
+                            name="VendorID",
+                            field_type=IntegerType(),
+                            required=False,
+                        ),
+                    ),
+                    required=True,
+                ),
+                NestedField(
+                    field_id=103,
+                    name="record_count",
+                    field_type=LongType(),
+                    doc="Number of records in the file",
+                    required=True,
+                ),
+                NestedField(
+                    field_id=104,
+                    name="file_size_in_bytes",
+                    field_type=LongType(),
+                    doc="Total file size in bytes",
+                    required=True,
+                ),
+                NestedField(
+                    field_id=105,
+                    name="block_size_in_bytes",
+                    field_type=LongType(),
+                    required=True,
+                ),
+                NestedField(
+                    field_id=108,
+                    name="column_sizes",
+                    field_type=MapType(
+                        key_id=117,
+                        key_type=IntegerType(),
+                        value_id=118,
+                        value_type=LongType(),
+                        value_required=True,
+                    ),
+                    doc="Map of column id to total size on disk",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=109,
+                    name="value_counts",
+                    field_type=MapType(
+                        key_id=119,
+                        key_type=IntegerType(),
+                        value_id=120,
+                        value_type=LongType(),
+                        value_required=True,
+                    ),
+                    doc="Map of column id to total count, including null and NaN",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=110,
+                    name="null_value_counts",
+                    field_type=MapType(
+                        key_id=121,
+                        key_type=IntegerType(),
+                        value_id=122,
+                        value_type=LongType(),
+                        value_required=True,
+                    ),
+                    doc="Map of column id to null value count",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=137,
+                    name="nan_value_counts",
+                    field_type=MapType(
+                        key_id=138,
+                        key_type=IntegerType(),
+                        value_id=139,
+                        value_type=LongType(),
+                        value_required=True,
+                    ),
+                    doc="Map of column id to number of NaN values in the column",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=125,
+                    name="lower_bounds",
+                    field_type=MapType(
+                        key_id=126,
+                        key_type=IntegerType(),
+                        value_id=127,
+                        value_type=BinaryType(),
+                        value_required=True,
+                    ),
+                    doc="Map of column id to lower bound",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=128,
+                    name="upper_bounds",
+                    field_type=MapType(
+                        key_id=129,
+                        key_type=IntegerType(),
+                        value_id=130,
+                        value_type=BinaryType(),
+                        value_required=True,
+                    ),
+                    doc="Map of column id to upper bound",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=131,
+                    name="key_metadata",
+                    field_type=BinaryType(),
+                    doc="Encryption key metadata blob",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=132,
+                    name="split_offsets",
+                    field_type=ListType(
+                        element_id=133,
+                        element_type=LongType(),
+                        element_required=True,
+                    ),
+                    doc="Splittable offsets",
+                    required=False,
+                ),
+                NestedField(
+                    field_id=140,
+                    name="sort_order_id",
+                    field_type=IntegerType(),
+                    doc="Sort order ID",
+                    required=False,
+                ),
+            ),
+            required=True,
+        ),
+        schema_id=1,
+        identifier_field_ids=[],
+    )
diff --git a/python/tests/io/__init__.py b/python/tests/io/__init__.py
index 00eaa2ffe46c..13a83393a912 100644
--- a/python/tests/io/__init__.py
+++ b/python/tests/io/__init__.py
@@ -1,11 +1,16 @@
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
 #
-#      http://www.apache.org/licenses/LICENSE-2.0
+#   http://www.apache.org/licenses/LICENSE-2.0
 #
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
diff --git a/python/tests/io/test_io_base.py b/python/tests/io/test_io_base.py
index 72495e19b6fe..9008c453a2ab 100644
--- a/python/tests/io/test_io_base.py
+++ b/python/tests/io/test_io_base.py
@@ -124,7 +124,7 @@ def delete(self, location: Union[str, InputFile, OutputFile]) -> None:
         try:
             os.remove(parsed_location.path)
         except FileNotFoundError as e:
-            raise FileNotFoundError(f"Cannot delete file, does not exist: {parsed_location.path} - Caused by: {e}")
+            raise FileNotFoundError(f"Cannot delete file, does not exist: {parsed_location.path} - Caused by: {e}") from e
 
 
 @pytest.mark.parametrize("CustomInputFile", [LocalInputFile, PyArrowFile])
diff --git a/python/tests/utils/test_schema_conversion.py b/python/tests/utils/test_schema_conversion.py
index 8776e1a14ffc..234ec1573f46 100644
--- a/python/tests/utils/test_schema_conversion.py
+++ b/python/tests/utils/test_schema_conversion.py
@@ -14,6 +14,8 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+from typing import Any, Dict
+
 import pytest
 
 from iceberg.schema import Schema
@@ -34,31 +36,29 @@
 from iceberg.utils.schema_conversion import AvroSchemaConversion
 
 
-def test_iceberg_to_avro(manifest_schema):
-    iceberg_schema = AvroSchemaConversion().avro_to_iceberg(manifest_schema)
+def test_iceberg_to_avro(avro_schema_manifest_file: Dict[str, Any]):
+    iceberg_schema = AvroSchemaConversion().avro_to_iceberg(avro_schema_manifest_file)
     expected_iceberg_schema = Schema(
         NestedField(
-            field_id=500, name="manifest_path", field_type=StringType(), required=False, doc="Location URI with FS scheme"
-        ),
-        NestedField(field_id=501, name="manifest_length", field_type=LongType(), required=False, doc="Total file size in bytes"),
-        NestedField(
-            field_id=502, name="partition_spec_id", field_type=IntegerType(), required=False, doc="Spec ID used to write"
+            field_id=500, name="manifest_path", field_type=StringType(), required=True, doc="Location URI with FS scheme"
         ),
+        NestedField(field_id=501, name="manifest_length", field_type=LongType(), required=True, doc="Total file size in bytes"),
+        NestedField(field_id=502, name="partition_spec_id", field_type=IntegerType(), required=True, doc="Spec ID used to write"),
         NestedField(
             field_id=503,
             name="added_snapshot_id",
             field_type=LongType(),
-            required=True,
+            required=False,
             doc="Snapshot ID that added the manifest",
         ),
         NestedField(
-            field_id=504, name="added_data_files_count", field_type=IntegerType(), required=True, doc="Added entry count"
+            field_id=504, name="added_data_files_count", field_type=IntegerType(), required=False, doc="Added entry count"
         ),
         NestedField(
-            field_id=505, name="existing_data_files_count", field_type=IntegerType(), required=True, doc="Existing entry count"
+            field_id=505, name="existing_data_files_count", field_type=IntegerType(), required=False, doc="Existing entry count"
         ),
         NestedField(
-            field_id=506, name="deleted_data_files_count", field_type=IntegerType(), required=True, doc="Deleted entry count"
+            field_id=506, name="deleted_data_files_count", field_type=IntegerType(), required=False, doc="Deleted entry count"
         ),
         NestedField(
             field_id=507,
@@ -66,45 +66,43 @@ def test_iceberg_to_avro(manifest_schema):
             field_type=ListType(
                 element_id=508,
                 element_type=StructType(
-                    fields=(
-                        NestedField(
-                            field_id=509,
-                            name="contains_null",
-                            field_type=BooleanType(),
-                            required=False,
-                            doc="True if any file has a null partition value",
-                        ),
-                        NestedField(
-                            field_id=518,
-                            name="contains_nan",
-                            field_type=BooleanType(),
-                            required=True,
-                            doc="True if any file has a nan partition value",
-                        ),
-                        NestedField(
-                            field_id=510,
-                            name="lower_bound",
-                            field_type=BinaryType(),
-                            required=True,
-                            doc="Partition lower bound for all files",
-                        ),
-                        NestedField(
-                            field_id=511,
-                            name="upper_bound",
-                            field_type=BinaryType(),
-                            required=True,
-                            doc="Partition upper bound for all files",
-                        ),
-                    )
+                    NestedField(
+                        field_id=509,
+                        name="contains_null",
+                        field_type=BooleanType(),
+                        required=True,
+                        doc="True if any file has a null partition value",
+                    ),
+                    NestedField(
+                        field_id=518,
+                        name="contains_nan",
+                        field_type=BooleanType(),
+                        required=False,
+                        doc="True if any file has a nan partition value",
+                    ),
+                    NestedField(
+                        field_id=510,
+                        name="lower_bound",
+                        field_type=BinaryType(),
+                        required=False,
+                        doc="Partition lower bound for all files",
+                    ),
+                    NestedField(
+                        field_id=511,
+                        name="upper_bound",
+                        field_type=BinaryType(),
+                        required=False,
+                        doc="Partition upper bound for all files",
+                    ),
                 ),
-                element_required=False,
+                element_required=True,
             ),
-            required=True,
+            required=False,
             doc="Summary for each partition",
         ),
-        NestedField(field_id=512, name="added_rows_count", field_type=LongType(), required=True, doc="Added rows count"),
-        NestedField(field_id=513, name="existing_rows_count", field_type=LongType(), required=True, doc="Existing rows count"),
-        NestedField(field_id=514, name="deleted_rows_count", field_type=LongType(), required=True, doc="Deleted rows count"),
+        NestedField(field_id=512, name="added_rows_count", field_type=LongType(), required=False, doc="Added rows count"),
+        NestedField(field_id=513, name="existing_rows_count", field_type=LongType(), required=False, doc="Existing rows count"),
+        NestedField(field_id=514, name="deleted_rows_count", field_type=LongType(), required=False, doc="Deleted rows count"),
         schema_id=1,
         identifier_field_ids=[],
     )
@@ -133,8 +131,8 @@ def test_avro_list_required_primitive():
         NestedField(
             field_id=100,
             name="array_with_string",
-            field_type=ListType(element_id=101, element_type=StringType(), element_required=False),
-            required=False,
+            field_type=ListType(element_id=101, element_type=StringType(), element_required=True),
+            required=True,
         ),
         schema_id=1,
     )
@@ -166,8 +164,8 @@ def test_avro_list_wrapped_primitive():
         NestedField(
             field_id=100,
             name="array_with_string",
-            field_type=ListType(element_id=101, element_type=StringType(), element_required=False),
-            required=False,
+            field_type=ListType(element_id=101, element_type=StringType(), element_required=True),
+            required=True,
         ),
         schema_id=1,
     )
@@ -217,13 +215,13 @@ def test_avro_list_required_record():
                 element_id=101,
                 element_type=StructType(
                     fields=(
-                        NestedField(field_id=102, name="contains_null", field_type=BooleanType(), required=False),
-                        NestedField(field_id=103, name="contains_nan", field_type=BooleanType(), required=True),
+                        NestedField(field_id=102, name="contains_null", field_type=BooleanType(), required=True),
+                        NestedField(field_id=103, name="contains_nan", field_type=BooleanType(), required=False),
                     )
                 ),
-                element_required=False,
+                element_required=True,
             ),
-            required=False,
+            required=True,
         ),
         schema_id=1,
         identifier_field_ids=[],
@@ -249,12 +247,12 @@ def test_nested_type():
 def test_map_type():
     avro_type = {
         "type": "map",
-        "values": ["long", "null"],
+        "values": ["null", "long"],
         "key-id": 101,
         "value-id": 102,
     }
     actual = AvroSchemaConversion()._convert_schema(avro_type)
-    expected = MapType(key_id=101, key_type=StringType(), value_id=102, value_type=LongType(), value_required=True)
+    expected = MapType(key_id=101, key_type=StringType(), value_id=102, value_type=LongType(), value_required=False)
     assert actual == expected
 
 
diff --git a/python/tests/utils/test_singleton.py b/python/tests/utils/test_singleton.py
new file mode 100644
index 000000000000..92b923dd820f
--- /dev/null
+++ b/python/tests/utils/test_singleton.py
@@ -0,0 +1,24 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from iceberg.avro.reader import BooleanReader, FixedReader
+
+
+def test_singleton():
+    """We want to reuse the readers to avoid creating a gazillion of them"""
+    assert id(BooleanReader()) == id(BooleanReader())
+    assert id(FixedReader(22)) == id(FixedReader(22))
+    assert id(FixedReader(19)) != id(FixedReader(25))