finish app develop

app/docx_parser.py

@@ -0,0 +1,67 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from pathlib import Path
+
+from docx import Document
+
+
+@dataclass(frozen=True)
+class Heading:
+    level: int
+    text: str
+
+
+@dataclass(frozen=True)
+class ParsedDocument:
+    filename: str
+    text: str
+    paragraphs: list[str]
+    headings: list[Heading]
+    tables: list[list[list[str]]]
+
+
+def _heading_level(style_name: str) -> int | None:
+    if not style_name.lower().startswith("heading"):
+        return None
+    parts = style_name.split()
+    if parts and parts[-1].isdigit():
+        return int(parts[-1])
+    return 1
+
+
+def parse_docx(path: Path | str, display_filename: str | None = None) -> ParsedDocument:
+    docx_path = Path(path)
+    document = Document(docx_path)
+    paragraphs: list[str] = []
+    headings: list[Heading] = []
+    tables: list[list[list[str]]] = []
+    text_parts: list[str] = []
+
+    for paragraph in document.paragraphs:
+        text = paragraph.text.strip()
+        if not text:
+            continue
+        paragraphs.append(text)
+        text_parts.append(text)
+        level = _heading_level(paragraph.style.name if paragraph.style else "")
+        if level is not None:
+            headings.append(Heading(level=level, text=text))
+
+    for table in document.tables:
+        rows: list[list[str]] = []
+        for row in table.rows:
+            values = [cell.text.strip() for cell in row.cells]
+            if any(values):
+                rows.append(values)
+                text_parts.append(" | ".join(values))
+        if rows:
+            tables.append(rows)
+
+    return ParsedDocument(
+        filename=display_filename or docx_path.name,
+        text="\n".join(text_parts),
+        paragraphs=paragraphs,
+        headings=headings,
+        tables=tables,
+    )