markdown-analysis 0.1.1__tar.gz → 0.1.3__tar.gz

{markdown_analysis-0.1.1 → markdown_analysis-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: markdown_analysis
-Version: 0.1.1
+Version: 0.1.3
 Summary: UNKNOWN
 Home-page: https://github.com/yannbanas/mrkdwn_analysis
 Author: yannbanas

{markdown_analysis-0.1.1 → markdown_analysis-0.1.3}/markdown_analysis.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: markdown-analysis
-Version: 0.1.1
+Version: 0.1.3
 Summary: UNKNOWN
 Home-page: https://github.com/yannbanas/mrkdwn_analysis
 Author: yannbanas

{markdown_analysis-0.1.1 → markdown_analysis-0.1.3}/mrkdwn_analysis/markdown_analyzer.py

@@ -284,19 +284,24 @@ class MarkdownParser:
         self.pos = self.length
 
     def parse_fenced_code_block(self, lang):
+        initial_line = self.pos
+        initial_indent = len(self.lines[self.pos]) - len(self.lines[self.pos].lstrip())
+        fence_marker = self.lines[self.pos].strip()[:3]  # Get ``` or ~~~
         self.pos += 1
         start = self.pos
+        
         while self.pos < self.length:
             line = self.lines[self.pos]
-            if line.strip().startswith('```'):
+            if line.strip() == fence_marker:
                 content = "\n".join(self.lines[start:self.pos])
                 self.tokens.append(BlockToken('code', content=content, meta={"language": lang}, line=start+1))
                 self.pos += 1
                 return
             self.pos += 1
-        content = "\n".join(self.lines[start:])
-        self.tokens.append(BlockToken('code', content=content, meta={"language": lang}, line=start+1))
-        self.pos = self.length
+            
+        # If we reach here, we didn't find the closing fence
+        self.pos = initial_line  # Reset position if fence not found
+        raise ValueError(f"Unclosed code fence starting at line {initial_line + 1}")
 
     def parse_blockquote(self):
         start = self.pos
@@ -553,3 +558,76 @@ class MarkdownAnalyzer:
             'characters': self.count_characters()
         }
         return analysis
+
+# =================== SUPPORT MDX ===================
+
+class MDXBlockToken(BlockToken):
+    def __init__(self, type_, content="", level=None, meta=None, line=None):
+        super().__init__(type_, content, level, meta, line)
+
+class MDXMarkdownParser(MarkdownParser):
+    JSX_IMPORT_RE = re.compile(r'^import\s+.*?\s+from\s+["\'](.*?)["\'];?\s*$')
+    JSX_COMPONENT_START_RE = re.compile(r'^<([A-Z][A-Za-z0-9]*|[a-z]+\.[A-Z][A-Za-z0-9]*).*?(?:>|\/>)$')
+    JSX_COMPONENT_END_RE = re.compile(r'^</([A-Z][A-Za-z0-9]*|[a-z]+\.[A-Z][A-Za-z0-9]*)>$')
+    
+    def __init__(self, text):
+        super().__init__(text)
+        self.in_jsx_block = False
+        self.current_jsx_content = []
+        self.jsx_start_line = None
+    
+    def handle_potential_hanging(self):
+        if self.pos >= self.length:
+            return False
+        line = self.lines[self.pos].strip()
+        if '</TabItem>' in line or '</Tabs>' in line:
+            self.pos += 1
+            return True
+        return False
+
+    def parse_fenced_code_block(self, lang):
+        initial_line = self.pos
+        self.pos += 1
+        content = []
+        
+        while self.pos < self.length:
+            line = self.lines[self.pos]
+            if line.strip() == '```':
+                if content:
+                    # Preserve proper indentation
+                    base_indent = min(len(line) - len(line.lstrip()) 
+                                   for line in content if line.strip())
+                    clean_content = []
+                    for line in content:
+                        if line.strip():
+                            clean_content.append('    ' + line[base_indent:])
+                    self.tokens.append(BlockToken('code', 
+                        content='\n'.join(clean_content),
+                        meta={"language": lang.strip(), "code_type": "fenced"},
+                        line=initial_line + 1))
+                self.pos += 1
+                return
+            content.append(line)
+            self.pos += 1
+
+    def parse(self):
+        self.tokens = []
+        while self.pos < self.length:
+            line = self.lines[self.pos].strip()
+            if self.FENCE_RE.match(line):
+                lang = self.FENCE_RE.match(line).group(1)
+                self.parse_fenced_code_block(lang)
+                continue
+            self.pos += 1
+        return self.tokens
+
+class MDXMarkdownAnalyzer(MarkdownAnalyzer):
+    def __init__(self, file_path, encoding='utf-8'):
+        with open(file_path, 'r', encoding=encoding) as f:
+            self.text = f.read()
+        parser = MDXMarkdownParser(self.text)
+        self.tokens = parser.parse()
+        self.references = parser.references
+        self.footnotes = parser.footnotes
+        self.inline_parser = InlineParser(references=self.references, footnotes=self.footnotes)
+        self._parse_inline_tokens()

{markdown_analysis-0.1.1 → markdown_analysis-0.1.3}/setup.py

@@ -6,7 +6,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name='markdown_analysis',
-    version='0.1.1',
+    version='0.1.3',
     long_description=long_description,
     long_description_content_type="text/markdown",
     author='yannbanas',