Skip to content

Commit

Permalink
Merge branch 'main' into markdown-link-browser-rendering
Browse files Browse the repository at this point in the history
  • Loading branch information
@drfho
drfho authored Dec 9, 2024
2 parents b91ebe7 + 7176e03 commit 79bec02
Show file tree
Hide file tree
Showing 7 changed files with 149 additions and 56 deletions.
124 changes: 88 additions & 36 deletions Products/zms/conf/metacmd_manager/manage_export_pydocx/manage_export_pydocx.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -186,6 +186,7 @@ def add_hyperlink(docx_block, link_text, url):
url_base = 'http://neon/'
# Omit javascript links
if not url.startswith('javascript:'):
url = url.replace('mailto:', '')
# Fix missing domain name
url = ('http' in url) and url.replace('http:///', url_base) or (url_base + (url.startswith('/') and url[1:] or url))
r_id = docx_block.part.relate_to(url, docx.opc.constants.RELATIONSHIP_TYPE.HYPERLINK, is_external=True)
Expand Down Expand Up @@ -222,7 +223,7 @@ def add_hyperlink(docx_block, link_text, url):
# #############################################

# Clean HTML
def clean_html(html):
def clean_html(html, wrap_trailling_text=False):
"""
Clean comments, styles, empty tags
and handle special characters: left-to-right, triangle
Expand All @@ -244,6 +245,9 @@ def clean_html(html):
html = html.replace(left_to_right_char,'')
html = html.replace('[[', triangle_char)
html = html.replace(']]', '')
if wrap_trailling_text:
# Wrap untagged text following a block element into a paragraph
html = re.sub(r'(?i)(?m)(<div.*?>.*?<\/div>)\s*(?=\w)(.*?)', r'\g<1>\n<p>\g<2><p>', html)
return html

# ADD RUNS TO DOCX-BLOCK
Expand Down Expand Up @@ -276,6 +280,8 @@ def add_runs(docx_block, bs_element):
docx_block.add_run(u'\U0000F021', style='Icon')
elif elrun.has_attr('class') and 'fa-phone' in elrun['class']:
docx_block.add_run(u'\U0000F028', style='Icon')
elif elrun.has_attr('class') and 'fa-exclamation-triangle' in elrun['class']:
docx_block.add_run(u'\U0000F045', style='Icon')
elif elrun.text != '':
docx_block.add_run(elrun.text).italic = True
elif elrun.text != '':
Expand All @@ -294,6 +300,8 @@ def add_runs(docx_block, bs_element):
docx_block.add_run(elrun.text).font.subscript = True
elif elrun.name == 'sup':
docx_block.add_run(elrun.text).font.superscript = True
elif elrun.name == 'u':
docx_block.add_run(elrun.text).underline = True
elif elrun.name == 'a':
if elrun.has_attr('href'):
add_hyperlink(docx_block = docx_block, link_text = elrun.text, url = elrun.get('href'))
Expand Down Expand Up @@ -355,6 +363,7 @@ def add_tagged_content_as_paragraph(docx_doc, bs_element, style_name="Standard",
def add_htmlblock_to_docx(zmscontext, docx_doc, htmlblock, zmsid=None, zmsmetaid=None):
# Clean HTML
htmlblock = clean_html(htmlblock)
htmlblock = htmlblock.strip()
heading_text = ''
# Apply BeautifulSoup and iterate over elements
soup = BeautifulSoup(htmlblock, 'html.parser')
Expand All @@ -376,20 +385,18 @@ def add_htmlblock_to_docx(zmscontext, docx_doc, htmlblock, zmsid=None, zmsmetaid
prepend_bookmark(p, zmsid)
else:
# #############################################
# HTML-Elements, element.name != None
# #############################################

# #############################################
# BLOCK-Elements, element.name != None
# ---------------------------------------------
# HEADINGS
# #############################################
if element.name in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
if element.name in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'h7', 'h8']:
heading_level = int(element.name[1])
heading_text = standard.pystr(element.text).strip()
p = add_heading(docx_doc, heading_text, level=heading_level)
if c==1 and zmsid:
prepend_bookmark(p, zmsid)
if element.text == 'Inhaltsverzeichnis':
p.style = docx_doc.styles['TOC-Header']
p.style = doc.styles['TOC-Header']
# #############################################
# PARAGRAPH
# #############################################
Expand All @@ -401,11 +408,14 @@ def add_htmlblock_to_docx(zmscontext, docx_doc, htmlblock, zmsid=None, zmsmetaid
# htmlblock.__contains__('ZMSTable') or htmlblock.__contains__('img')
if element.has_attr('class'):
if 'caption' in element['class'] and zmsmetaid in ['ZMSGraphic', 'ZMSTable']:
p.style = docx_doc.styles['caption']
p.style = doc.styles['caption']
else:
class_name = element['class'][0]
style_name = (class_name in docx_doc.styles) and class_name or 'Normal'
p.style = docx_doc.styles[style_name]
try:
style_name = (class_name in doc.styles) and class_name or 'Normal'
except:
style_name = 'Normal'
p.style = doc.styles[style_name]
add_runs(docx_block = p, bs_element = element)

## Remove empty paragraphs
Expand Down Expand Up @@ -495,7 +505,7 @@ def add_list(docx_obj, element, level=0, c=0):
# ------------------------------------------------
def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
'''Convert cell html to docx'''
cl_html = clean_html(docx_cell.text)
cl_html = clean_html(docx_cell.text, wrap_trailling_text=True)
cl_type = cl_html.startswith('[th:') and 'th' or 'td'
cl_html = re.sub(r'\[(th|td):\d:\d\] ','',cl_html)
cl = BeautifulSoup(cl_html, 'html.parser')
Expand All @@ -509,7 +519,14 @@ def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
try:
if {'div','ol','ul','table','p'} & set([e.name for e in cl.children]):
# [A] Block elements
add_htmlblock_to_docx(zmscontext, docx_cell, cl_html, zmsid=None)
try:
add_htmlblock_to_docx(zmscontext, docx_cell, cl_html, zmsid=None)
except:
p.add_run('Rendering Error Table-Cell: %s'%cl.text)
# Cleaning: remove first cell paragraph if empty
if docx_cell.paragraphs[0].text == '':
first_p = docx_cell.paragraphs[0]._element
docx_cell._tc.remove(first_p)
elif set([e.name for e in cl.children])==set([None]):
# [B] Just text
p.text = cl.text
Expand Down Expand Up @@ -547,7 +564,7 @@ def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
img_src = zmscontext.operator_getattr(zmscontext,zmsid).attr('imghires').getHref(zmscontext.REQUEST)
except:
pass
img_name = img_src.split('/')[-1]
img_name = img_src.split('?')[0].split('/')[-1]
if not img_src.startswith('http'):
src_url0 = zmscontext.absolute_url().split('/content/')[0]
src_url1 = img_src.split('/content/')[-1]
Expand Down Expand Up @@ -583,12 +600,34 @@ def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
elif element.name == 'div':
if element.has_attr('class') and (('ZMSGraphic' in element['class']) or ('graphic' in element['class'])):
ZMSGraphic_html = standard.pystr(''.join([str(e) for e in element.children]))
zmsid = element.has_attr('id') and element['id'] or zmsid
zmscontext = zmscontext.operator_getattr(zmscontext,zmsid)
add_htmlblock_to_docx(zmscontext, docx_doc, ZMSGraphic_html, zmsid, zmsmetaid='ZMSGraphic')
elif element.has_attr('class') and ('ZMSTextarea' in element['class']):
ZMSTextarea_html = standard.pystr(''.join([str(e) for e in element.children]))
zmsid = element.has_attr('id') and element['id'] or zmsid
zmscontext = zmscontext.operator_getattr(zmscontext,zmsid)
add_htmlblock_to_docx(zmscontext, docx_doc, ZMSTextarea_html, zmsid, zmsmetaid='ZMSTextarea')
elif element.has_attr('class') and 'handlungsaufforderung' in element['class']:
add_tagged_content_as_paragraph(docx_doc, element, 'Handlungsaufforderung', c, zmsid)
if len([e.name for e in element.children if e.name in ['ul','ol']])>0:
add_tagged_content_as_paragraph(docx_doc, element, 'Handlungsaufforderung', c, zmsid)
child_tag = [e.name for e in element.children if e.name][0]
# COPY add_list
def add_list(docx_obj, element, level=0, c=0):
for i, li in enumerate(element.find_all('li', recursive=False)):
if docx_obj.paragraphs and docx_obj.paragraphs[-1].text == '':
p = docx_obj.paragraphs[-1]
else:
p = docx_obj.add_paragraph()
p = set_block_as_listitem(p, list_type=element.name, level=level, i=i)
add_runs(docx_block = p, bs_element = li)
if c==1 and zmsid:
prepend_bookmark(p, zmsid)
for ul in li.find_all(['ul','ol'], recursive=False):
add_list(docx_doc, ul, level+1)
add_list(docx_doc, element.find(child_tag), level=1, c=c)
else:
add_tagged_content_as_paragraph(docx_doc, element, 'Handlungsaufforderung', c, zmsid)
elif element.has_attr('class') and 'grundsatz' in element['class']:
add_tagged_content_as_paragraph(docx_doc, element, 'Grundsatz', c, zmsid)
elif element.has_attr('style') and 'background: rgb(238, 238, 238)' in element['style'] \
Expand All @@ -601,14 +640,14 @@ def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
add_runs(docx_block = p, bs_element = element)
else:
child_tags = [e.name for e in element.children if e.name]
if {'em','strong','i', 'span'} & set(child_tags):
if {'em','strong','i','span','u'} & set(child_tags):
p = docx_doc.add_paragraph()
if c==1 and zmsid:
prepend_bookmark(p, zmsid)
if len(element.contents) == 1:
if element.has_attr('class'):
style_name = (class_name in docx_doc.styles) and class_name or 'Normal'
p.style = docx_doc.styles[style_name]
style_name = (class_name in doc.styles) and class_name or 'Normal'
p.style = doc.styles[style_name]
p.add_run(element.text)
elif len(element.contents) > 1:
for e in element.contents:
Expand All @@ -621,8 +660,15 @@ def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
# p.add_run('Routing: ')
p.add_run(u'\U0000F028', style='Icon')
p.add_run(' ')
elif 'fa-exclamation-triangle' in class_name:
# p.add_run('Kommentar: ')
p.add_run(u'\U0000F045', style='Icon')
p.add_run(' ')
if list(e.children)!=[]:
add_runs(docx_block = p, bs_element = e)
if [ch.name for ch in e.children if ch.name in ['p', 'ol', 'ul', 'div']]:
add_htmlblock_to_docx(zmscontext, docx_doc, standard.pystr(e), zmsid)
else:
add_runs(docx_block = p, bs_element = e)
else:
p.add_run(standard.pystr(e.text))
elif e.name:
Expand Down Expand Up @@ -678,15 +724,19 @@ def convert_cell_html_to_docx(zmscontext, docx_cell, text_style='Normal'):
for input_field in element.find_all('input', recursive=True):
input_field_count += 1
p.add_run('%s. <input> : %s\n'%(input_field_count, input_field.get('name','')))

# #############################################
# OTHERS
# OTHER ELEMENTS
# #############################################
elif element.name == 'hr':
# Omit horizontal rule
pass
elif element.name == 'script':
# Omit javascript
pass
elif element.name == 'style':
# Omit style
pass
else:
try:
if element.has_text:
Expand All @@ -705,7 +755,7 @@ def add_breadcrumbs_as_runs(zmscontext, p):
c = 0
for obj in breadcrumbs:
c += 1
link_text = obj.meta_id == 'ZMS' and standard.pystr(obj.attr('title')) or standard.pystr(obj.attr('titlealt'))
link_text = obj.meta_id == 'ZMS' and standard.pystr(obj.attr('title')) or standard.pystr(obj.getTitlealt(zmscontext.REQUEST))
add_hyperlink(docx_block = p, link_text = link_text, url = obj.getHref2IndexHtml(zmscontext.REQUEST))
if c < len(breadcrumbs):
p.add_run(' > ')
Expand Down Expand Up @@ -755,7 +805,9 @@ def apply_standard_json_docx(self):

zmscontext = self
request = zmscontext.REQUEST
# For debugging use preview content
# request.set('preview', 'preview')
# #################################
is_page = zmscontext.isPage()

id = zmscontext.id
Expand Down Expand Up @@ -794,7 +846,7 @@ def apply_standard_json_docx(self):
pageelements = [ \
e for e in zmscontext.getChildNodes(request) \
if ( ( e.getType() in [ 'ZMSObject', 'ZMSRecordSet'] ) \
and not e.meta_id in [ 'LgChangeHistory','ZMSTeaserContainer','LgELearningBanner'] \
and not e.meta_id in [ 'LgChangeHistory','ZMSTeaserContainer'] \
and not e.isPage() ) \
or e.meta_id in [ 'ZMSLinkElement' ]
]
Expand Down Expand Up @@ -832,7 +884,7 @@ def apply_standard_json_docx(self):
'parent_id':parent_id,
'parent_meta_id':parent_meta_id,
'docx_format':'image',
'imgwidth': imgwidth,
'imgwidth': imgwidth,
'imgheight':imgheight,
'content':img_url
},
Expand Down Expand Up @@ -938,7 +990,7 @@ def apply_standard_json_docx(self):
}]

# Give some customizing hints for standard_html
if pageelement.meta_id in ['LgRegel','LgBedingung','LgELearningBanner','ZMSNote']:
if pageelement.meta_id in ['LgRegel','LgBedingung','LgELearningBanner','ZMSNote','ZMSTestarea']:
standard.writeStdout(None, 'IMPORTANT NOTE: %s.standard_html needs to be customized!'%(pageelement.meta_id))
# %<---- CUSTOMIZE LIKE THIS ---------------------
# zmi python:request['URL'].find('/manage')>0 and not request['URL'].find('pydocx')>0;
Expand Down Expand Up @@ -1057,6 +1109,7 @@ def add_heading(self, text, level=1):
# binary data of the DOCX file.
def manage_export_pydocx(self, save_file=True, file_name=None):
request = self.REQUEST
request.set('lang', self.getPrimaryLanguage())
docx_creator = request.AUTHENTICATED_USER.getUserName()

# PAGE_COUNTER: Counter for recursive export
Expand Down Expand Up @@ -1207,22 +1260,21 @@ def manage_export_pydocx(self, save_file=True, file_name=None):
# #############################################
# [4] CAPTION TEXT-BLOCK
elif v and block['docx_format']=='Caption':
if re.match(r'^\[Abb. e\d+\] .*', v):
capt_list = re.split(r'^\[Abb. e\d+\] ', v)
if len(capt_list) > 1 and len(capt_list[1]) > 0:
p = doc.add_paragraph(style='Caption')
prepend_bookmark(p, block['id'])
p.add_run('Abb. %s: '%block['id']).font.italic = False
p.add_run(capt_list[1])
elif re.match(r'^\[Abb. e\d+\] ', v):
# Omit caption with empty text
pass
p = doc.add_paragraph(style='Caption')
if re.match(r'^\[Abb\. e\d+\] .*', v):
re_list = re.split(r'^(\[Abb. e\d+\]) (.*)',v)
v1 = re_list[1]
v2 = BeautifulSoup(re_list[2], 'html.parser').get_text()
p.add_run(v1).font.italic = False
p.add_run(' ')
p.add_run(v2)
else:
p = doc.add_paragraph(style='Caption')
prepend_bookmark(p, block['id'])
p.add_run(v)
prepend_bookmark(p, block['id'])

# #############################################
# [5] TEXT-BLOCK with given block format (style)
elif v and block['docx_format'] in [e.name for e in doc.styles]:
elif v and ( block['docx_format'] in [e.name for e in doc.styles] or block['docx_format'] in [e.name.replace(' ','') for e in doc.styles] ):
p = doc.add_paragraph(v, style=block['docx_format'])
prepend_bookmark(p, block['id'])
elif v:
Expand Down
Binary file modified Products/zms/conf/metacmd_manager/manage_export_pydocx/neon.docx
View file
Binary file not shown.
17 changes: 15 additions & 2 deletions Products/zms/conf/metacmd_manager/manage_export_pydocx/readme.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,19 @@ pip install python-docx

## Configuration and Customization

Ensure that the script is configured correctly with the necessary parameters for your specific use case (especially the global variable `docx_tmpl` as filesystem path to the DOCX file that is used as a template). You may need to modify the script to fit your data source and desired output format.
Some (complex) ZMS content objects may need another template `standard_json_docx` (Python script) to generate a normalized JSON representation of the object's content. The standard content model contains some examples of the script. For further details, please refer to the docstring of
Ensure that the script is configured correctly with the necessary parameters for your specific use case, especially the global variable `docx_tmpl` as filesystem path to the DOCX file that is used as a template:

```py
# Set local path for docx-template
docx_tmpl = open("/home/zope/src/zms-publishing/ZMS5/Products/zms/conf/metacmd_manager/manage_export_pydocx/neon.docx", "rb")
```

You may prefer to export not the committed but the working content, so set the REQUEST-variable:

```py
# For debugging use preview content
request.set('preview', 'preview')
```

Furthermore You may need to modify the script to fit your data source and desired output format. Some (complex) ZMS content objects may need another template `standard_json_docx` (Python script) to generate a normalized JSON representation of the object's content. The standard content model contains some examples of the script. For further details, please refer to the docstring of
`manage_export_pydocx.apply_standard_json_docx()`.
17 changes: 14 additions & 3 deletions Products/zms/conf/metacmd_manager/manage_export_pydocx/styles.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,8 @@
<w:unhideWhenUsed/>
<w:qFormat/>
<w:pPr>
<w:keepNext/>
<w:keepLines/>
<w:spacing w:before="480" w:after="0" w:line="288" w:lineRule="auto"/>
<w:outlineLvl w:val="1"/>
</w:pPr>
Expand All @@ -126,6 +128,8 @@
<w:unhideWhenUsed/>
<w:qFormat/>
<w:pPr>
<w:keepNext/>
<w:keepLines/>
<w:spacing w:before="440" w:after="0"/>
<w:outlineLvl w:val="2"/>
</w:pPr>
Expand All @@ -145,6 +149,8 @@
<w:unhideWhenUsed/>
<w:qFormat/>
<w:pPr>
<w:keepNext/>
<w:keepLines/>
<w:spacing w:before="280" w:after="0"/>
<w:outlineLvl w:val="3"/>
</w:pPr>
Expand All @@ -166,11 +172,15 @@
<w:unhideWhenUsed/>
<w:qFormat/>
<w:pPr>
<w:keepNext/>
<w:keepLines/>
<w:spacing w:before="200" w:after="0"/>
<w:outlineLvl w:val="4"/>
</w:pPr>
<w:rPr>
<w:color w:val="auto"/>
<w:bCs w:val="0"/>
<w:i/>
<w:iCs/>
<w:sz w:val="18"/>
</w:rPr>
</w:style>
Expand All @@ -190,9 +200,10 @@
<w:outlineLvl w:val="5"/>
</w:pPr>
<w:rPr>
<w:i/>
<w:bCs w:val="0"/>
<w:u w:val="single"/>
<w:iCs/>
<w:color w:val="243F60" w:themeColor="accent1" w:themeShade="7F"/>
<w:sz w:val="18"/>
</w:rPr>
</w:style>

Expand Down
Loading

0 comments on commit 79bec02

Please sign in to comment.