import json
|
import re
|
import hashlib
|
import zipfile
|
import sys
|
from pathlib import Path
|
from xml.etree import ElementTree as ET
|
|
SOURCE = Path(r'C:\Users\云\Desktop\SOP-QC-YL')
|
sys.stdout.reconfigure(encoding='utf-8')
|
OUT = Path('scripts/sop-qc')
|
OUT.mkdir(exist_ok=True)
|
W = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}'
|
|
def clean(value):
|
return re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f]', '', value).replace('\r', '\n').strip()
|
|
def word_text(node):
|
output = []
|
for run in node.iter(W+'r'):
|
text = ''.join(n.text or '' if n.tag in (W+'t', W+'delText') else '\t' if n.tag == W+'tab' else '\n' if n.tag in (W+'br', W+'cr') else '' for n in run.iter())
|
alignment = run.find(W+'rPr/'+W+'vertAlign')
|
if alignment is not None and alignment.get(W+'val') == 'superscript' and text.strip():
|
text = '^('+text+')'
|
output.append(text)
|
return clean(''.join(output))
|
|
records = []
|
for file in sorted(SOURCE.iterdir(), key=lambda p: p.name):
|
if file.name.startswith('~$') or file.suffix.lower() not in ('.doc', '.docx'):
|
continue
|
blocks = []
|
if file.suffix.lower() == '.docx':
|
with zipfile.ZipFile(file) as z:
|
body = ET.fromstring(z.read('word/document.xml')).find(W+'body')
|
for node in body:
|
if node.tag == W+'p':
|
blocks.append({'p': word_text(node)})
|
elif node.tag == W+'tbl':
|
blocks.append({'table': [[ '\n'.join(word_text(p) for p in cell.findall(W+'p')).strip() for cell in row.findall(W+'tc')] for row in node.findall(W+'tr')]})
|
else:
|
body = ET.parse(OUT/'extracted'/(file.name+'.xml')).getroot()
|
for node in body:
|
if node.tag == 'p':
|
blocks.append({'p': clean(node.text or '')})
|
elif node.tag == 'table':
|
blocks.append({'table': [[clean('\n'.join(p.text or '' for p in cell)) for cell in row] for row in node]})
|
text = '\n'.join(b.get('p', '\n'.join(' | '.join(row) for row in b.get('table', []))) for b in blocks)
|
records.append({'file': file.name, 'sha256': hashlib.sha256(file.read_bytes()).hexdigest(), 'blocks': blocks, 'text': text})
|
(OUT/'extracted'/(file.name+'.txt')).write_text(text, encoding='utf-8')
|
(OUT/'documents.json').write_text(json.dumps(records, ensure_ascii=False, indent=2), encoding='utf-8')
|
print(json.dumps({'documents': len(records), 'tables': sum(sum('table' in b for b in d['blocks']) for d in records)}, ensure_ascii=False))
|
