feat: export core Hermes skills

2026-07-15 02:45:56 +00:00
parent a028b63eda
commit 54711fee2a
308 changed files with 41310 additions and 1 deletions
@@ -0,0 +1,116 @@
+"""
+Standalone function to add comments to a .docx file using zipfile + lxml.
+Use AFTER ContractEditor.save() since ContractEditor rewrites document.xml.
+
+Usage:
+    from add_comments_to_docx import add_comments_to_docx
+    # comments = [(anchor_text, comment_text), ...]
+    placed = add_comments_to_docx('/tmp/【修】contract.docx', comments)
+"""
+import zipfile, io
+from datetime import datetime
+from lxml import etree
+
+W = 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
+R_NS = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships'
+
+def qn(tag):
+    return f'{{{W}}}{tag}'
+
+def add_comments_to_docx(filepath, comments, author='WB'):
+    """Add comments to a docx file.
+    
+    Args:
+        filepath: path to docx (modified in place)
+        comments: list of (anchor_text, comment_text) tuples
+        author: comment author name (default 'WB')
+    
+    Returns:
+        int: number of comments successfully placed
+    """
+    with open(filepath, 'rb') as f:
+        data = f.read()
+    zin = zipfile.ZipFile(io.BytesIO(data))
+    buf = io.BytesIO()
+    zout = zipfile.ZipFile(buf, 'w', zipfile.ZIP_DEFLATED)
+    doc_xml = zin.read('word/document.xml')
+    doc_tree = etree.fromstring(doc_xml)
+    body = doc_tree.find(qn('body'))
+    
+    nsmap = {'w': W, 'r': R_NS}
+    comments_xml = etree.Element(qn('comments'), nsmap=nsmap)
+    
+    comment_id = 200
+    placed = 0
+    
+    for anchor_text, comment_text in comments:
+        cid = str(comment_id)
+        comment_id += 1
+        
+        # Create comment element
+        comment_el = etree.SubElement(comments_xml, qn('comment'))
+        comment_el.set(qn('id'), cid)
+        comment_el.set(qn('author'), author)
+        comment_el.set(qn('date'), datetime.now().strftime('%Y-%m-%dT%H:%M:%SZ'))
+        cp = etree.SubElement(comment_el, qn('p'))
+        cr = etree.SubElement(cp, qn('r'))
+        ct = etree.SubElement(cr, qn('t'))
+        ct.set('{http://www.w3.org/XML/1998/namespace}space', 'preserve')
+        ct.text = comment_text
+        
+        # Find anchor in document
+        for p in body.iter(qn('p')):
+            runs = p.findall(f'.//{qn("r")}')
+            full = ''.join(''.join(t.text or '' for t in r.findall(qn('t'))) for r in runs)
+            if anchor_text in full:
+                # Insert commentRangeStart at beginning of paragraph
+                crs = etree.Element(qn('commentRangeStart'))
+                crs.set(qn('id'), cid)
+                p.insert(0, crs)
+                
+                # Append commentRangeEnd + reference
+                cre = etree.Element(qn('commentRangeEnd'))
+                cre.set(qn('id'), cid)
+                p.append(cre)
+                
+                ref_run = etree.SubElement(p, qn('r'))
+                ref_rpr = etree.SubElement(ref_run, qn('rPr'))
+                ref_style = etree.SubElement(ref_rpr, qn('rStyle'))
+                ref_style.set(qn('val'), 'CommentReference')
+                ref_cr = etree.SubElement(ref_run, qn('commentReference'))
+                ref_cr.set(qn('id'), cid)
+                
+                placed += 1
+                break
+    
+    # Rewrite zip
+    for item in zin.namelist():
+        if item == 'word/document.xml':
+            zout.writestr(item, etree.tostring(doc_tree, xml_declaration=True, encoding='UTF-8', standalone=True))
+        elif item == '[Content_Types].xml':
+            ct_xml = zin.read(item)
+            ct_tree = etree.fromstring(ct_xml)
+            if not any('comments.xml' in (el.get('PartName') or '') for el in ct_tree):
+                override = etree.SubElement(ct_tree, 'Override')
+                override.set('PartName', '/word/comments.xml')
+                override.set('ContentType', 'application/vnd.openxmlformats-officedocument.wordprocessingml.comments+xml')
+            zout.writestr(item, etree.tostring(ct_tree, xml_declaration=True, encoding='UTF-8', standalone=True))
+        elif item == 'word/_rels/document.xml.rels':
+            rels_xml = zin.read(item)
+            rels_tree = etree.fromstring(rels_xml)
+            if not any('comments.xml' in (el.get('Target') or '') for el in rels_tree):
+                rel = etree.SubElement(rels_tree, 'Relationship')
+                rel.set('Id', f'rId{len(rels_tree) + 10}')
+                rel.set('Type', 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments')
+                rel.set('Target', 'comments.xml')
+            zout.writestr(item, etree.tostring(rels_tree, xml_declaration=True, encoding='UTF-8', standalone=True))
+        else:
+            zout.writestr(item, zin.read(item))
+    
+    zout.writestr('word/comments.xml', etree.tostring(comments_xml, xml_declaration=True, encoding='UTF-8', standalone=True))
+    zout.close()
+    zin.close()
+    
+    with open(filepath, 'wb') as f:
+        f.write(buf.getvalue())
+    return placed