markdowndata 0.0.6__py3-none-any.whl → 0.1.1__py3-none-any.whl

markdowndata/content_parser.py

@@ -32,17 +32,12 @@ def detect_value_type(text: str) -> str | None:
     return 'md_text'
 
 
-def yaml_dict_parser(text: str) -> dict:
+def yaml_parser(text: str) -> dict:
     """
-    Parse YAML from a string (surrounded by ===) and returns it as a dictionary.
-    Assumes YAML is a block at the beginning of the text.
+    Parse YAML from a string (surrounded by ===)
     """
     match = re.search(r'===\s*\n(.*?)\n===', text, re.DOTALL)
-    if match:
-        yaml_data = yaml.safe_load(match.group(1))
-        if yaml_data:
-            return {k: convert_value(v) for k, v in yaml_data.items()}
-    return {}
+    return yaml.safe_load(match.group(1))
 
 
 def md_table_parser(text: str) -> list[dict]:
@@ -167,7 +162,7 @@ def parse_content_block(text: str):
         raise ValueError(f'No parser found for content: {text}')
 
     parser_functions = {
-        'yaml_dict': yaml_dict_parser,
+        'yaml_dict': yaml_parser,
         'md_table': md_table_parser,
         'md_list': md_list_parser,
         'md_text': md_text_parser

markdowndata/process_markdown.py

@@ -41,12 +41,8 @@ class MarkDataParser:
         for node in sections:
             sub_dict = self.build_dict(node.subsections)
 
-            if isinstance(node.parsed, dict):
-                # If the parsed content is a dictionary, merge it with its subsections
-                merged = {**node.parsed, **sub_dict}
-            elif node.subsections:
-                # If subsections exist but parsed content is not a dict,
-                # wrap both into a new dictionary
+            if node.subsections:
+                # If subsections exist and there is parsed content wrap both into a new dictionary
                 merged = {
                     'content': node.parsed,
                     **sub_dict

markdowndata/section_tree.py

@@ -9,7 +9,15 @@ def split_sections(text: str):
     Each section is identified by a header (e.g., #, ##, ###).
     """
     pattern = re.compile(r'^(?P<header>#+) (?P<title>[^\n]+)', re.MULTILINE)
-    matches = list(pattern.finditer(text))
+    code_spans = [match.span() for match in re.finditer(r'```.*?```', text, re.DOTALL)]
+
+    def is_in_code_block(pos: int) -> bool:
+        for start, end in code_spans:
+            if start <= pos < end:
+                return True
+        return False
+
+    matches = [match for match in pattern.finditer(text) if not is_in_code_block(match.start())]
 
     sections = []
 

{markdowndata-0.0.6.dist-info → markdowndata-0.1.1.dist-info}/METADATA

@@ -1,8 +1,9 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: markdowndata
-Version: 0.0.6
+Version: 0.1.1
 Summary: Tool to convert markdown tables into json objects
 License: MIT
+License-File: LICENSE
 Author: Gordon Bean
 Author-email: gbean@cs.byu.edu
 Requires-Python: >=3.10,<4.0
@@ -12,6 +13,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Requires-Dist: bs4 (>=0.0.2,<0.0.3)
 Requires-Dist: markdown-it-py (>=3.0.0,<4.0.0)
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)

markdowndata-0.1.1.dist-info/RECORD

@@ -0,0 +1,9 @@
+markdowndata/__init__.py,sha256=jB8leosqIVXuO4LmU0KWn3OyJwgAtGKQBab9JUsbSQ0,172
+markdowndata/content_parser.py,sha256=x0ellHrZn6RZynUzwFGnxdzhS_Y2tL33zzvKrEwBSQc,5157
+markdowndata/process_markdown.py,sha256=jswWDnkApAMoT1gEXe2dfSB2pHt6U3vFuWrh6PgQjBY,1981
+markdowndata/section_tree.py,sha256=qCKZHO4mUJqdVD81tqeIlETRK4Esk6z9XZ90IM6LNOA,3032
+markdowndata/utils.py,sha256=jVTKEGZiLCKdv1cS-73iMf_GaXT6cBc3cl9tp_fjKOw,2040
+markdowndata-0.1.1.dist-info/METADATA,sha256=hfZuT7qF8jNhqMIaycyfVzxxLqC9DPUKzfl0yX7LtM4,706
+markdowndata-0.1.1.dist-info/WHEEL,sha256=kJCRJT_g0adfAJzTx2GUMmS80rTJIVHRCfG0DQgLq3o,88
+markdowndata-0.1.1.dist-info/licenses/LICENSE,sha256=K-k1T7XcwAVVmLsHhfWMye6r7p45xz3xwv5S5FBSyZE,1074
+markdowndata-0.1.1.dist-info/RECORD,,

{markdowndata-0.0.6.dist-info → markdowndata-0.1.1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.1.3
+Generator: poetry-core 2.3.1
 Root-Is-Purelib: true
 Tag: py3-none-any

markdowndata-0.0.6.dist-info/RECORD

@@ -1,9 +0,0 @@
-markdowndata/__init__.py,sha256=jB8leosqIVXuO4LmU0KWn3OyJwgAtGKQBab9JUsbSQ0,172
-markdowndata/content_parser.py,sha256=FdapNfkvCj71K5lUSGQh0H1jS5vF36-l1EImsX28J2o,5387
-markdowndata/process_markdown.py,sha256=hcG7X-zdVTl3zHqPjSBYkmwo2Hg0YQYIDhEKeRhpQOo,2193
-markdowndata/section_tree.py,sha256=gn6PtzXcg4iN7F8Tldy3p3jrWe9IYqrcDEAjNm940ME,2722
-markdowndata/utils.py,sha256=jVTKEGZiLCKdv1cS-73iMf_GaXT6cBc3cl9tp_fjKOw,2040
-markdowndata-0.0.6.dist-info/LICENSE,sha256=K-k1T7XcwAVVmLsHhfWMye6r7p45xz3xwv5S5FBSyZE,1074
-markdowndata-0.0.6.dist-info/METADATA,sha256=CeBPGYKdAft1cxA5DGZ1v7Ebgx1DTKNxrIKTwYRgJsg,633
-markdowndata-0.0.6.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-markdowndata-0.0.6.dist-info/RECORD,,