Issue 990 (#1002)

* #1001

changelog.md

@@ -15,6 +15,8 @@
 - [Issue 994](https://github.com/jackdewinter/pymarkdown/issues/994)
   - Verified behavior of Rule Md029, adding configuration for starting ordered
     lists from integers greater than 1
+- [Issue 1001](https://github.com/jackdewinter/pymarkdown/issues/1001)
+  - Verified behavior of rules Md019 and Md021, fixing issues with Md021
 
 ### Changed
 

publish/coverage.json

@@ -2,12 +2,12 @@
     "projectName": "pymarkdown",
     "reportSource": "pytest",
     "branchLevel": {
-        "totalMeasured": 4823,
-        "totalCovered": 4823
+        "totalMeasured": 4831,
+        "totalCovered": 4831
     },
     "lineLevel": {
-        "totalMeasured": 19417,
-        "totalCovered": 19417
+        "totalMeasured": 19442,
+        "totalCovered": 19442
     }
 }
 

publish/test-results.json

@@ -1220,7 +1220,7 @@
         },
         {
             "name": "test.rules.test_md019",
-            "totalTests": 21,
+            "totalTests": 47,
             "failedTests": 0,
             "errorTests": 0,
             "skippedTests": 0,
@@ -1236,7 +1236,7 @@
         },
         {
             "name": "test.rules.test_md021",
-            "totalTests": 20,
+            "totalTests": 53,
             "failedTests": 0,
             "errorTests": 0,
             "skippedTests": 0,
@@ -1604,7 +1604,7 @@
         },
         {
             "name": "test.test_markdown_extra",
-            "totalTests": 114,
+            "totalTests": 115,
             "failedTests": 0,
             "errorTests": 0,
             "skippedTests": 0,

pymarkdown/plugins/rule_md_019.py

@@ -72,18 +72,19 @@ def next_token(self, context: PluginScanContext, token: MarkdownToken) -> None:
             self.__atx_heading_token = None
         elif token.is_text:
             text_token = cast(TextMarkdownToken, token)
-            resolved_extracted_whitespace = ParserHelper.remove_all_from_text(
-                text_token.extracted_whitespace
-            )
-            if self.__atx_heading_token and "\t" in resolved_extracted_whitespace:
-                start_index = (
-                    self.__atx_heading_token.column_number
-                    - 1
-                    + self.__atx_heading_token.hash_count
-                )
-                resolved_extracted_whitespace = TabHelper.detabify_string(
-                    resolved_extracted_whitespace, start_index
+            if self.__atx_heading_token:
+                resolved_extracted_whitespace = ParserHelper.remove_all_from_text(
+                    text_token.extracted_whitespace
                 )
-            if self.__atx_heading_token and len(resolved_extracted_whitespace) > 1:
-                self.__report(context, text_token)
+                if "\t" in resolved_extracted_whitespace:
+                    start_index = (
+                        self.__atx_heading_token.column_number
+                        - 1
+                        + self.__atx_heading_token.hash_count
+                    )
+                    resolved_extracted_whitespace = TabHelper.detabify_string(
+                        resolved_extracted_whitespace, start_index
+                    )
+                if len(resolved_extracted_whitespace) > 1:
+                    self.__report(context, text_token)
             self.__atx_heading_token = None

pymarkdown/plugins/rule_md_021.py

@@ -5,6 +5,8 @@
 
 from typing import Optional, cast
 
+from pymarkdown.general.parser_helper import ParserHelper
+from pymarkdown.general.tab_helper import TabHelper
 from pymarkdown.plugin_manager.plugin_details import PluginDetailsV2
 from pymarkdown.plugin_manager.plugin_scan_context import PluginScanContext
 from pymarkdown.plugin_manager.rule_plugin import RulePlugin
@@ -21,9 +23,10 @@ class RuleMd021(RulePlugin):
 
     def __init__(self) -> None:
         super().__init__()
-        self.__atx_heading_token: Optional[MarkdownToken] = None
+        self.__atx_heading_token: Optional[AtxHeadingMarkdownToken] = None
         self.__is_left_in_error = False
         self.__first_text_token: Optional[TextMarkdownToken] = None
+        self.__last_token: Optional[TextMarkdownToken] = None
 
     def get_details(self) -> PluginDetailsV2:
         """
@@ -45,13 +48,11 @@ def starting_new_file(self) -> None:
         """
         self.__atx_heading_token = None
         self.__first_text_token = None
+        self.__last_token = None
         self.__is_left_in_error = False
 
     def __report(
-        self,
-        context: PluginScanContext,
-        token: MarkdownToken,
-        end_token: EndMarkdownToken,
+        self, context: PluginScanContext, token: MarkdownToken, extra_end_data: str
     ) -> None:
         assert self.__atx_heading_token is not None
         if context.in_fix_mode:
@@ -64,10 +65,7 @@ def __report(
                     "extracted_whitespace",
                     " ",
                 )
-            if (
-                end_token.extra_end_data is not None
-                and len(end_token.extra_end_data) > 1
-            ):
+            if len(extra_end_data) > 1:
                 self.register_fix_token_request(
                     context,
                     token,
@@ -78,24 +76,61 @@ def __report(
         else:
             self.report_next_token_error(context, self.__atx_heading_token)
 
+    def __handle_atx_end(
+        self, context: PluginScanContext, token: MarkdownToken
+    ) -> None:
+        end_token = cast(EndMarkdownToken, token)
+        assert end_token.extra_end_data is not None
+        extra_end_data = end_token.extra_end_data
+        if "\t" in extra_end_data:
+            assert self.__last_token is not None
+            assert self.__last_token.is_text
+            resolved_token_text = ParserHelper.remove_all_from_text(
+                self.__last_token.token_text
+            )
+            start_index = self.__last_token.column_number - 1
+            resolved_token_text = TabHelper.detabify_string(
+                resolved_token_text, start_index
+            )
+            start_index_after_last_text_token = start_index + len(resolved_token_text)
+            extra_end_data = TabHelper.detabify_string(
+                extra_end_data, start_index_after_last_text_token
+            )
+        if self.__is_left_in_error or len(extra_end_data) > 1:
+            self.__report(context, token, extra_end_data)
+        self.__atx_heading_token = None
+        self.__first_text_token = None
+        self.__last_token = None
+
     def next_token(self, context: PluginScanContext, token: MarkdownToken) -> None:
         """
         Event that a new token is being processed.
         """
         if token.is_atx_heading:
             atx_token = cast(AtxHeadingMarkdownToken, token)
             if atx_token.remove_trailing_count:
-                self.__atx_heading_token = token
+                self.__atx_heading_token = atx_token
             self.__is_left_in_error = False
         elif token.is_paragraph_end:
             self.__atx_heading_token = None
         elif token.is_atx_heading_end:
-            end_token = cast(EndMarkdownToken, token)
-            assert end_token.extra_end_data is not None
-            if self.__is_left_in_error or len(end_token.extra_end_data) > 1:
-                self.__report(context, token, end_token)
+            self.__handle_atx_end(context, token)
         elif token.is_text:
             text_token = cast(TextMarkdownToken, token)
-            self.__first_text_token = text_token
-            if self.__atx_heading_token and len(text_token.extracted_whitespace) > 1:
-                self.__is_left_in_error = True
+            if not self.__first_text_token and self.__atx_heading_token:
+                resolved_extracted_whitespace = ParserHelper.remove_all_from_text(
+                    text_token.extracted_whitespace
+                )
+                if "\t" in resolved_extracted_whitespace:
+                    start_index = (
+                        self.__atx_heading_token.column_number
+                        - 1
+                        + self.__atx_heading_token.hash_count
+                    )
+                    resolved_extracted_whitespace = TabHelper.detabify_string(
+                        resolved_extracted_whitespace, start_index
+                    )
+                if len(resolved_extracted_whitespace) > 1:
+                    self.__is_left_in_error = True
+                self.__first_text_token = text_token
+            self.__last_token = text_token

test/api/test_api_scan.py

@@ -268,20 +268,24 @@ def test_api_scan_with_multiple_scan_issues():
 
     # Assert
     assert scan_result
-    assert len(scan_result.scan_failures) == 5
+    assert len(scan_result.scan_failures) == 6
+    print(scan_result.scan_failures)
     assert scan_result.scan_failures[0].partial_equals(
         PyMarkdownScanFailure(source_path, 1, 1, "MD022", "", "", None)
     )
     assert scan_result.scan_failures[1].partial_equals(
         PyMarkdownScanFailure(source_path, 1, 12, "MD010", "", "", None)
     )
     assert scan_result.scan_failures[2].partial_equals(
-        PyMarkdownScanFailure(source_path, 2, 2, "MD022", "", "", None)
+        PyMarkdownScanFailure(source_path, 2, 2, "MD021", "", "", None)
     )
     assert scan_result.scan_failures[3].partial_equals(
-        PyMarkdownScanFailure(source_path, 2, 2, "MD023", "", "", None)
+        PyMarkdownScanFailure(source_path, 2, 2, "MD022", "", "", None)
     )
     assert scan_result.scan_failures[4].partial_equals(
+        PyMarkdownScanFailure(source_path, 2, 2, "MD023", "", "", None)
+    )
+    assert scan_result.scan_failures[5].partial_equals(
         PyMarkdownScanFailure(source_path, 2, 14, "MD010", "", "", None)
     )
 

test/rules/test_md005.py

@@ -780,7 +780,7 @@
     ),
     pluginRuleTest(
         "mix_md005_md007_only_md005_1",
-        disable_rules="md007",
+        disable_rules=__plugin_disable_md007,
         source_file_contents=""" + first
    + second
      + third
@@ -803,7 +803,7 @@
     ),
     pluginRuleTest(
         "mix_md005_md007_only_md005_2",
-        disable_rules="md007",
+        disable_rules=__plugin_disable_md007,
         source_file_contents=""" + first
     + second
        + third

test/rules/test_md006.py

@@ -188,8 +188,8 @@
     pluginRuleTest(
         "mix_md006_md004",
         is_mix_test=True,
-        enable_rules="MD006",
-        disable_rules="MD007",
+        enable_rules=plugin_enable_this_rule,
+        disable_rules=__plugin_disable_md007,
         source_file_contents=""" + first
    * second
      - third
@@ -225,7 +225,7 @@ def test_md006_scan(test: pluginRuleTest) -> None:
     """
     Execute a parameterized scan test for plugin md001.
     """
-    execute_scan_test(test, "md006")
+    execute_scan_test(test, plugin_enable_this_rule)
 
 
 @pytest.mark.parametrize("test", fixTests, ids=id_test_plug_rule_fn)

test/rules/test_md007.py

@@ -530,7 +530,7 @@
     ),
     pluginRuleTest(
         "mix_md007_md005_only_md007_1",
-        disable_rules="md005",
+        disable_rules=__plugin_disable_md005,
         source_file_contents=""" + first
    + second
      + third
@@ -553,7 +553,7 @@
     ),
     pluginRuleTest(
         "mix_md007_md005_only_md007_2",
-        disable_rules="md005",
+        disable_rules=__plugin_disable_md005,
         source_file_contents=""" + first
    + second
      + third
@@ -621,7 +621,7 @@
     ),
     pluginRuleTest(
         "mix_md007_md030_xx",
-        disable_rules="MD030",
+        disable_rules=__plugin_disable_md030,
         source_file_contents=""" *  First
     first paragraph
 
@@ -646,7 +646,7 @@
     ),
     pluginRuleTest(
         "mix_md007_md030",
-        disable_rules="md005",
+        disable_rules=__plugin_disable_md005,
         source_file_contents=""" *  First
     first paragraph