feat(data-process): 增加 Office 原文件预览接口
This commit is contained in:
caoxiaozhu
308
backend/app/modules/data_process/office_preview.py
Normal file
308
backend/app/modules/data_process/office_preview.py
Normal file
@@ -0,0 +1,308 @@
|
||||
"""Word 与 Excel 原文件的安全、受限预览模型。
|
||||
|
||||
预览只返回浏览器绘制所需的结构化数据，不返回或执行 Office 包中的活动内容。
|
||||
DOCX 的字符偏移与上传时的正文抽取规则保持一致，供前端定位当前切片。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
from docx import Document
|
||||
from docx.oxml.table import CT_Tbl
|
||||
from docx.oxml.text.paragraph import CT_P
|
||||
from docx.table import Table
|
||||
from docx.text.paragraph import Paragraph
|
||||
from openpyxl import load_workbook
|
||||
|
||||
from app.modules.data_process.algorithms import (
|
||||
_MAX_WORKBOOK_COLUMNS,
|
||||
_MAX_WORKBOOK_HEADER_SCAN_ROWS,
|
||||
_infer_xlsx_header_region,
|
||||
_normalize_spreadsheet_value,
|
||||
_rewrite_xlsx_workbook_relationships,
|
||||
_validate_office_archive,
|
||||
_xlsx_sheet_merge_ranges,
|
||||
normalize_text,
|
||||
)
|
||||
|
||||
MAX_DOCX_PREVIEW_BLOCKS = 2_000
|
||||
MAX_XLSX_PREVIEW_ROWS = 200
|
||||
|
||||
|
||||
def _docx_alignment(paragraph: Paragraph) -> str:
|
||||
value = paragraph.alignment
|
||||
return {
|
||||
0: "left",
|
||||
1: "center",
|
||||
2: "right",
|
||||
3: "justify",
|
||||
4: "distribute",
|
||||
5: "justify",
|
||||
7: "justify",
|
||||
8: "distribute",
|
||||
9: "distribute",
|
||||
}.get(int(value) if value is not None else -1, "left")
|
||||
|
||||
|
||||
def _docx_heading_level(paragraph: Paragraph) -> int | None:
|
||||
style = paragraph.style
|
||||
if style is None:
|
||||
return None
|
||||
style_name = str(style.name or "")
|
||||
style_id = str(style.style_id or "")
|
||||
match = re.search(r"(?:heading|标题)\s*([1-6])", f"{style_name} {style_id}", re.IGNORECASE)
|
||||
return int(match.group(1)) if match else None
|
||||
|
||||
|
||||
def build_docx_preview(raw: bytes) -> dict[str, Any]:
|
||||
"""把 DOCX 转为保留标题、段落和表格顺序的浏览器预览模型。"""
|
||||
|
||||
_validate_office_archive(raw, "docx")
|
||||
try:
|
||||
document = Document(io.BytesIO(raw))
|
||||
except Exception as exc:
|
||||
raise ValueError(f"invalid DOCX file: {exc}") from exc
|
||||
|
||||
blocks: list[dict[str, Any]] = []
|
||||
source_cursor = 0
|
||||
has_source_content = False
|
||||
rendered_blocks = 0
|
||||
truncated = False
|
||||
|
||||
def source_range(value: str) -> tuple[str, int, int] | None:
|
||||
nonlocal source_cursor, has_source_content
|
||||
text = normalize_text(value)
|
||||
if not text:
|
||||
return None
|
||||
if has_source_content:
|
||||
source_cursor += 2
|
||||
start = source_cursor
|
||||
source_cursor += len(text)
|
||||
has_source_content = True
|
||||
return text, start, source_cursor
|
||||
|
||||
for child in document.element.body.iterchildren():
|
||||
if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
|
||||
truncated = True
|
||||
break
|
||||
|
||||
if isinstance(child, CT_P):
|
||||
paragraph = Paragraph(child, document)
|
||||
located = source_range(paragraph.text)
|
||||
if located is None:
|
||||
continue
|
||||
text, start, end = located
|
||||
style_name = str(paragraph.style.name or "") if paragraph.style else ""
|
||||
blocks.append(
|
||||
{
|
||||
"type": "paragraph",
|
||||
"text": text,
|
||||
"style": style_name,
|
||||
"heading_level": _docx_heading_level(paragraph),
|
||||
"alignment": _docx_alignment(paragraph),
|
||||
"is_list": "list" in style_name.casefold() or "列表" in style_name,
|
||||
"source_start": start,
|
||||
"source_end": end,
|
||||
}
|
||||
)
|
||||
rendered_blocks += 1
|
||||
continue
|
||||
|
||||
if not isinstance(child, CT_Tbl):
|
||||
continue
|
||||
table = Table(child, document)
|
||||
preview_rows: list[dict[str, Any]] = []
|
||||
for row in table.rows:
|
||||
if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
|
||||
truncated = True
|
||||
break
|
||||
cell_values = [normalize_text(cell.text) for cell in row.cells]
|
||||
located = source_range("\t".join(cell_values))
|
||||
if located is None:
|
||||
continue
|
||||
_, start, end = located
|
||||
preview_rows.append(
|
||||
{
|
||||
"cells": cell_values,
|
||||
"source_start": start,
|
||||
"source_end": end,
|
||||
}
|
||||
)
|
||||
rendered_blocks += 1
|
||||
if preview_rows:
|
||||
blocks.append({"type": "table", "rows": preview_rows})
|
||||
if truncated:
|
||||
break
|
||||
|
||||
return {
|
||||
"format": "docx",
|
||||
"blocks": blocks,
|
||||
"truncated": truncated,
|
||||
}
|
||||
|
||||
|
||||
def build_xlsx_preview(
|
||||
raw: bytes,
|
||||
*,
|
||||
sheet_index: int = 0,
|
||||
offset: int = 0,
|
||||
limit: int = 100,
|
||||
) -> dict[str, Any]:
|
||||
"""按工作表分页返回 XLSX 的表头和记录网格。"""
|
||||
|
||||
if sheet_index < 0 or offset < 0:
|
||||
raise ValueError("sheet_index and offset must be non-negative")
|
||||
if limit < 1 or limit > MAX_XLSX_PREVIEW_ROWS:
|
||||
raise ValueError(
|
||||
f"XLSX preview limit must be in [1, {MAX_XLSX_PREVIEW_ROWS}]"
|
||||
)
|
||||
|
||||
_validate_office_archive(raw, "xlsx")
|
||||
merged_by_sheet, normalized_targets = _xlsx_sheet_merge_ranges(raw)
|
||||
workbook_raw = (
|
||||
_rewrite_xlsx_workbook_relationships(raw, normalized_targets)
|
||||
if normalized_targets
|
||||
else raw
|
||||
)
|
||||
try:
|
||||
workbook = load_workbook(
|
||||
io.BytesIO(workbook_raw),
|
||||
read_only=True,
|
||||
data_only=True,
|
||||
keep_links=False,
|
||||
)
|
||||
except Exception as exc:
|
||||
raise ValueError(f"invalid XLSX file: {exc}") from exc
|
||||
|
||||
try:
|
||||
sheets = [
|
||||
{
|
||||
"index": index,
|
||||
"name": worksheet.title,
|
||||
"state": worksheet.sheet_state,
|
||||
}
|
||||
for index, worksheet in enumerate(workbook.worksheets)
|
||||
]
|
||||
if not sheets:
|
||||
raise ValueError("XLSX workbook contains no worksheets")
|
||||
if sheet_index >= len(sheets):
|
||||
raise ValueError("XLSX worksheet index is out of range")
|
||||
|
||||
worksheet = workbook.worksheets[sheet_index]
|
||||
reset_dimensions = getattr(worksheet, "reset_dimensions", None)
|
||||
if callable(reset_dimensions):
|
||||
reset_dimensions()
|
||||
row_iterator = enumerate(worksheet.iter_rows(values_only=True), start=1)
|
||||
buffered_rows: dict[int, tuple[Any, ...]] = {}
|
||||
|
||||
def normalized_values(row: tuple[Any, ...]) -> list[Any]:
|
||||
values = list(row)
|
||||
while values and values[-1] in {None, ""}:
|
||||
values.pop()
|
||||
if len(values) > _MAX_WORKBOOK_COLUMNS:
|
||||
raise ValueError(
|
||||
f"XLSX worksheet {worksheet.title!r} exceeds "
|
||||
f"{_MAX_WORKBOOK_COLUMNS} columns"
|
||||
)
|
||||
return values
|
||||
|
||||
for row_number, row in row_iterator:
|
||||
values = normalized_values(row)
|
||||
if not values or all(value in {None, ""} for value in values):
|
||||
continue
|
||||
buffered_rows[row_number] = tuple(values)
|
||||
if len(buffered_rows) >= _MAX_WORKBOOK_HEADER_SCAN_ROWS:
|
||||
break
|
||||
|
||||
if not buffered_rows:
|
||||
return {
|
||||
"format": "xlsx",
|
||||
"sheets": sheets,
|
||||
"active_sheet": {
|
||||
"index": sheet_index,
|
||||
"name": worksheet.title,
|
||||
"columns": [],
|
||||
"rows": [],
|
||||
"offset": offset,
|
||||
"limit": limit,
|
||||
"has_more": False,
|
||||
},
|
||||
}
|
||||
|
||||
_, header_end_row, headers = _infer_xlsx_header_region(
|
||||
worksheet.title,
|
||||
buffered_rows,
|
||||
merged_by_sheet.get(worksheet.title, ()),
|
||||
)
|
||||
preview_rows: list[dict[str, Any]] = []
|
||||
record_index = 0
|
||||
has_more = False
|
||||
|
||||
def append_row(row_number: int, values: tuple[Any, ...] | list[Any]) -> bool:
|
||||
nonlocal record_index, has_more
|
||||
row_values = list(values)
|
||||
if len(row_values) > len(headers):
|
||||
raise ValueError(
|
||||
f"XLSX worksheet {worksheet.title!r} has a row wider than its header"
|
||||
)
|
||||
row_values.extend([None] * (len(headers) - len(row_values)))
|
||||
record = {
|
||||
header: _normalize_spreadsheet_value(value)
|
||||
for header, value in zip(headers, row_values, strict=True)
|
||||
}
|
||||
if not any(value not in {"", None} for value in record.values()):
|
||||
return False
|
||||
current_index = record_index
|
||||
record_index += 1
|
||||
if current_index < offset:
|
||||
return False
|
||||
if len(preview_rows) >= limit:
|
||||
has_more = True
|
||||
return True
|
||||
preview_rows.append(
|
||||
{
|
||||
"row_number": row_number,
|
||||
"record_index": current_index,
|
||||
"values": [record[header] for header in headers],
|
||||
"record": record,
|
||||
}
|
||||
)
|
||||
return False
|
||||
|
||||
for row_number, values in buffered_rows.items():
|
||||
if row_number > header_end_row and append_row(row_number, values):
|
||||
break
|
||||
else:
|
||||
for row_number, row in row_iterator:
|
||||
values = normalized_values(row)
|
||||
if not values or all(value in {None, ""} for value in values):
|
||||
continue
|
||||
if append_row(row_number, values):
|
||||
break
|
||||
|
||||
return {
|
||||
"format": "xlsx",
|
||||
"sheets": sheets,
|
||||
"active_sheet": {
|
||||
"index": sheet_index,
|
||||
"name": worksheet.title,
|
||||
"columns": headers,
|
||||
"rows": preview_rows,
|
||||
"offset": offset,
|
||||
"limit": limit,
|
||||
"has_more": has_more,
|
||||
},
|
||||
}
|
||||
finally:
|
||||
workbook.close()
|
||||
|
||||
|
||||
__all__ = [
|
||||
"MAX_DOCX_PREVIEW_BLOCKS",
|
||||
"MAX_XLSX_PREVIEW_ROWS",
|
||||
"build_docx_preview",
|
||||
"build_xlsx_preview",
|
||||
]
|
||||
Reference in New Issue
Block a user