markdowndata 0.0.5__tar.gz → 0.1.0__tar.gz

{markdowndata-0.0.5 → markdowndata-0.1.0}/PKG-INFO

@@ -1,8 +1,9 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: markdowndata
-Version: 0.0.5
+Version: 0.1.0
 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-0.0.5 → markdowndata-0.1.0}/markdowndata/__init__.py

@@ -7,4 +7,4 @@ def loads(text):
 
 
 def load(file):
-    return loads(file.read())
+    return loads(file.read())

{markdowndata-0.0.5 → markdowndata-0.1.0}/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-0.0.5 → markdowndata-0.1.0}/markdowndata/process_markdown.py

@@ -1,4 +1,5 @@
 from typing import List
+
 from .content_parser import parse_content_block
 from .section_tree import split_sections, build_section_tree
 from .utils import Node
@@ -9,6 +10,7 @@ class MarkDataParser:
     Parses a Markdown document into a JSON-like dictionary structure.
     Builds a hierarchy of sections and converts each section's content into a structured form.
     """
+
     def __init__(self):
         self.data = {}
 
@@ -29,7 +31,7 @@ class MarkDataParser:
 
         # Convert the section tree into a JSON-like dictionary structure
         self.data = self.build_dict(section_tree)
-        return self.data
+        return self.data['Root']
 
     def build_dict(self, sections: List[Node]) -> dict:
         """
@@ -39,12 +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
@@ -55,4 +53,5 @@ class MarkDataParser:
 
             # Use the node's title as the key in the dictionary
             result[node.title] = merged
+
         return result

{markdowndata-0.0.5 → markdowndata-0.1.0}/markdowndata/section_tree.py

@@ -12,6 +12,17 @@ def split_sections(text: str):
     matches = list(pattern.finditer(text))
 
     sections = []
+
+    # First grab anything before the initial header
+    end = matches[0].start() if matches else len(text)
+    sections.append(Section(
+        title="",  # The section's title text
+        level=0,  # The number of # symbols indicates nesting level
+        start=0,  # Position where this header starts in the text
+        end=end,  # Position where this section's content ends
+        content=text[:end].strip()  # The actual text content of this section (excluding header)
+    ))
+
     for i, match in enumerate(matches):
         # Calculate the 'end' of the current section:
         # It's the start of the next header or the end of the document.
@@ -34,6 +45,12 @@ def build_section_tree(sections):
     Uses a stack to track the current section hierarchy.
     """
     root = Node(title='Root', level=0, parsed={}, subsections=[])
+
+    # If the initial section is level 0, it makes part of the root
+    if sections[0].level == 0:
+        root.parsed = parse_content_block(sections[0].content)
+        sections.pop(0)
+
     stack = [root]
 
     for section in sections:
@@ -55,4 +72,4 @@ def build_section_tree(sections):
         # Push this node to the stack (might have its own children)
         stack.append(node)
 
-    return root.subsections
+    return [root]

{markdowndata-0.0.5 → markdowndata-0.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "markdowndata"
-version = "0.0.5"
+version = "0.1.0"
 description = "Tool to convert markdown tables into json objects"
 authors = ["Gordon Bean <gbean@cs.byu.edu>", "Robert Greathouse <robbykap@byu.edu>"]
 license = "MIT"