Merge pull request #436 from manish2202/master

Aho-Corasick algorithm implementation in Python

Aho-Corasick Algorithm/aho_corasick1.py

@@ -0,0 +1,65 @@
+# Python implementation of Aho-Corasick string matching
+FAIL = -1
+
+def aho_corasick(string, keywords):
+    transitions = {}
+    outputs = {}
+    fails = {}
+
+    new_state = 0
+
+    for keyword in keywords:
+        state = 0
+
+        for j, char in enumerate(keyword):
+            res = transitions.get((state, char), FAIL)
+            if res == FAIL:
+                break
+            state = res
+
+        for char in keyword[j:]:
+            new_state += 1
+            transitions[(state, char)] = new_state
+            state = new_state
+
+        outputs[state] = [keyword]
+
+    queue = []
+    for (from_state, char), to_state in transitions.items():
+        if from_state == 0 and to_state != 0:
+            queue.append(to_state)
+            fails[to_state] = 0
+
+    while queue:
+        r = queue.pop(0)
+        for (from_state, char), to_state in transitions.items():
+            if from_state == r:
+                queue.append(to_state)
+                state = fails[from_state]
+
+                while True:
+                    res = transitions.get((state, char), state and FAIL)
+                    if res != FAIL:
+                        break
+                    state = fails[state]
+
+                failure = transitions.get((state, char), state and FAIL)
+                fails[to_state] = failure
+                outputs.setdefault(to_state, []).extend(
+                    outputs.get(failure, []))
+
+    state = 0
+    results = []
+    for i, char in enumerate(string):
+        while True:
+            res = transitions.get((state, char), state and FAIL)
+            if res != FAIL:
+                state = res
+                break
+            state = fails[state]
+
+        for match in outputs.get(state, ()):
+            pos = i - len(match) + 1
+            results.append((pos, match))
+
+    return results

Aho-Corasick Algorithm/requirements

@@ -0,0 +1,192 @@
+alabaster==0.7.12
+asn1crypto==0.24.0
+astroid==2.2.5
+astropy==3.2.1
+attrs==19.1.0
+Babel==2.7.0
+backcall==0.1.0
+backports.functools-lru-cache==1.5
+backports.os==0.1.1
+backports.shutil-get-terminal-size==1.0.0
+backports.tempfile==1.0
+bitarray==0.9.3
+bkcharts==0.2
+bleach==3.1.0
+bokeh==1.2.0
+boto==2.49.0
+Bottleneck==1.2.1
+certifi==2019.6.16
+cffi==1.12.3
+chardet==3.0.4
+Click==7.0
+cloudpickle==1.2.1
+clyent==1.2.2
+colorama==0.4.1
+comtypes==1.1.7
+contextlib2==0.5.5
+cycler==0.10.0
+Cython==0.29.12
+cytoolz==0.10.0
+dask==2.1.0
+decorator==4.4.0
+defusedxml==0.6.0
+distributed==2.1.0
+docutils==0.14
+entrypoints==0.3
+et-xmlfile==1.0.1
+fastcache==1.1.0
+filelock==3.0.12
+Flask==1.1.1
+future==0.17.1
+gevent==1.4.0
+glob2==0.7
+greenlet==0.4.15
+h5py==2.9.0
+heapdict==1.0.0
+idna==2.8
+imageio==2.5.0
+imagesize==1.1.0
+importlib-metadata==0.17
+ipykernel==5.1.1
+ipython==7.6.1
+ipython-genutils==0.2.0
+ipywidgets==7.5.0
+isort==4.3.21
+itsdangerous==1.1.0
+jdcal==1.4.1
+jedi==0.13.3
+Jinja2==2.10.1
+joblib==0.13.2
+json5==0.8.4
+jsonschema==3.0.1
+jupyter==1.0.0
+jupyter-client==5.3.1
+jupyter-console==6.0.0
+jupyter-core==4.5.0
+jupyterlab==1.0.2
+jupyterlab-server==1.0.0
+keyring==18.0.0
+kiwisolver==1.1.0
+lazy-object-proxy==1.4.1
+libarchive-c==2.8
+llvmlite==0.29.0
+locket==0.2.0
+lxml==4.3.4
+MarkupSafe==1.1.1
+matplotlib==3.1.0
+mccabe==0.6.1
+menuinst==1.4.16
+mistune==0.8.4
+mkl-fft==1.0.12
+mkl-random==1.0.2
+mkl-service==2.0.2
+mock==3.0.5
+more-itertools==7.0.0
+mpmath==1.1.0
+msgpack==0.6.1
+multipledispatch==0.6.0
+navigator-updater==0.2.1
+nbconvert==5.5.0
+nbformat==4.4.0
+networkx==2.3
+nltk==3.4.4
+nose==1.3.7
+notebook==6.0.0
+numba==0.44.1
+numexpr==2.6.9
+numpy==1.16.4
+numpydoc==0.9.1
+olefile==0.46
+openpyxl==2.6.2
+packaging==19.0
+pandas==0.24.2
+pandocfilters==1.4.2
+parso==0.5.0
+partd==1.0.0
+path.py==12.0.1
+pathlib2==2.3.4
+patsy==0.5.1
+pep8==1.7.1
+pickleshare==0.7.5
+Pillow==6.1.0
+pkginfo==1.5.0.1
+pluggy==0.12.0
+ply==3.11
+prometheus-client==0.7.1
+prompt-toolkit==2.0.9
+psutil==5.6.3
+py==1.8.0
+pycodestyle==2.5.0
+pycosat==0.6.3
+pycparser==2.19
+pycrypto==2.6.1
+pycurl==7.43.0.3
+pyflakes==2.1.1
+Pygments==2.4.2
+pylint==2.3.1
+pyodbc==4.0.26
+pyOpenSSL==19.0.0
+pyparsing==2.4.0
+pyreadline==2.1
+pyrsistent==0.14.11
+PySocks==1.7.0
+pytest==5.0.1
+pytest-arraydiff==0.3
+pytest-astropy==0.5.0
+pytest-doctestplus==0.3.0
+pytest-openfiles==0.3.2
+pytest-remotedata==0.3.1
+python-dateutil==2.8.0
+pytz==2019.1
+PyWavelets==1.0.3
+pywin32==223
+pywinpty==0.5.5
+PyYAML==5.1.1
+pyzmq==18.0.0
+QtAwesome==0.5.7
+qtconsole==4.5.1
+QtPy==1.8.0
+requests==2.22.0
+rope==0.14.0
+ruamel-yaml==0.15.46
+scikit-image==0.15.0
+scikit-learn==0.21.2
+scipy==1.2.1
+seaborn==0.9.0
+Send2Trash==1.5.0
+simplegeneric==0.8.1
+singledispatch==3.4.0.3
+six==1.12.0
+snowballstemmer==1.9.0
+sortedcollections==1.1.2
+sortedcontainers==2.1.0
+soupsieve==1.8
+spyder-kernels==0.5.1
+SQLAlchemy==1.3.5
+statsmodels==0.10.0
+stopwords==0.1.3
+sympy==1.4
+tables==3.5.2
+tblib==1.4.0
+terminado==0.8.2
+testpath==0.4.2
+toolz==0.10.0
+tornado==6.0.3
+tqdm==4.32.1
+traitlets==4.3.2
+unicodecsv==0.14.1
+urllib3==1.24.2
+wcwidth==0.1.7
+webencodings==0.5.1
+Werkzeug==0.15.4
+widgetsnbextension==3.5.0
+win-inet-pton==1.1.0
+win-unicode-console==0.5
+wincertstore==0.2
+wrapt==1.11.2
+xlrd==1.2.0
+XlsxWriter==1.1.8
+xlwings==0.15.8
+xlwt==1.3.0
+zict==1.0.0
+zipp==0.5.1