feat(markdown): implement GFM table parser

src/markdown_table.py

@@ -1,10 +1,51 @@
+import re
 from dataclasses import dataclass
 
+_TABLE_SEPARATOR = re.compile(r"^\|?\s*:?-{2,}:?\s*(\|\s*:?-{2,}:?\s*)+\|?\s*$")
+
 @dataclass(frozen=True)
 class TableBlock:
+ """Frozen GFM table block.
+ [C: src/markdown_helper.py:MarkdownRenderer.render]
+ """
  headers: list[str]
  rows: list[list[str]]
  span: tuple[int, int]
 
+def _split_row(line: str) -> list[str]:
+ line = line.strip()
+ if line.startswith("|"): line = line[1:]
+ if line.endswith("|"): line = line[:-1]
+ return [c.strip() for c in line.split("|")]
+
+def _is_table_at(lines: list[str], i: int) -> bool:
+ if i + 1 >= len(lines): return False
+ if "|" not in lines[i]: return False
+ return bool(_TABLE_SEPARATOR.match(lines[i + 1]))
+
 def parse_tables(text: str) -> list[TableBlock]:
- return []
+ lines = text.splitlines()
+ in_fence = False
+ blocks: list[TableBlock] = []
+ i = 0
+ while i < len(lines):
+  line = lines[i]
+  if line.strip().startswith("```"):
+   in_fence = not in_fence
+   i += 1
+   continue
+  if in_fence:
+   i += 1
+   continue
+  if _is_table_at(lines, i):
+   headers = _split_row(lines[i])
+   j = i + 2
+   rows: list[list[str]] = []
+   while j < len(lines) and "|" in lines[j] and not _TABLE_SEPARATOR.match(lines[j]):
+    rows.append(_split_row(lines[j]))
+    j += 1
+   blocks.append(TableBlock(headers=headers, rows=rows, span=(i, j)))
+   i = j
+   continue
+  i += 1
+ return blocks