"""docx.py — the .docx surface projector: an OWN minimal OOXML emitter.
Own-the-core: a .docx is just a ZIP of a few XML parts (WordprocessingML). We
emit it with the standard library only — ``zipfile`` + string XML — no
python-docx, no external dependency. This proves a "richer structured format"
surface without importing anyone else's toolkit.
Parts emitted (the minimal valid set + a styles part for real headings):
[Content_Types].xml
_rels/.rels
word/_rels/document.xml.rels
word/styles.xml (Title / Heading1 / Heading2 / Normal)
word/document.xml (the content)
Like the markdown projector it reads only the IR's realized sentences; it
invents nothing. The surface differs, the faithful content does not.
"""
from __future__ import annotations
import io
import os
import sys
import zipfile
from xml.sax.saxutils import escape
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from document_ir import DocumentIR # noqa: E402
from projectors.base import register # noqa: E402
_CONTENT_TYPES = """
"""
_RELS = """
"""
_DOC_RELS = """
"""
_W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
_STYLES = f"""
"""
def _para(text: str, style: str | None = None) -> str:
ppr = f"" if style else ""
return (f"{ppr}"
f"{escape(text)}")
class DocxProjector:
surface = "docx"
media_type = ("application/vnd.openxmlformats-officedocument."
"wordprocessingml.document")
ext = "docx"
modality = "text"
def _document_xml(self, doc: DocumentIR) -> str:
body: list[str] = [_para(doc.title, "Title")]
if doc.subtitle:
body.append(_para(doc.subtitle, "Subtitle"))
abstract = doc.meta.get("abstract")
if abstract is not None and abstract.sentences:
body.append(_para(abstract.text()))
for sec in doc.sections:
style = "Heading1" if sec.level <= 1 else "Heading2"
body.append(_para(sec.heading, style))
for block in sec.blocks:
t = block.text()
if t:
body.append(_para(t))
return (f""
f""
+ "".join(body)
+ ""
"")
def project(self, doc: DocumentIR) -> bytes:
buf = io.BytesIO()
with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as z:
z.writestr("[Content_Types].xml", _CONTENT_TYPES)
z.writestr("_rels/.rels", _RELS)
z.writestr("word/_rels/document.xml.rels", _DOC_RELS)
z.writestr("word/styles.xml", _STYLES)
z.writestr("word/document.xml", self._document_xml(doc))
return buf.getvalue()
register(DocxProjector())