def __store_with_attachments(dst_dir, filename, text, all_docs, ref, root_dir):
"""
Store text in dst_dir/filename, create dir if necessary and copy attachments.
"""
path = __store_file(dst_dir, filename, text)
root_doc = XML.xpath_node(all_docs, ".//document[.//*/@ref='"+ref+"']")
rel_dir = XML.xpath_plain(root_doc, "@dir")
src_dir = os.path.join(root_dir, rel_dir)
attachments = XML.xpath_list(root_doc, "_meta/attachment")
for att in attachments:
att_path = XML.xpath_plain(att, "@to_path")
att_rel_path = os.path.relpath(att_path, start=rel_dir)
src_att = os.path.join(src_dir, att_rel_path)
dst_att = os.path.join(dst_dir, att_rel_path)
dst_dir_att = os.path.dirname(dst_att)
if not os.path.exists(dst_dir_att):
os.makedirs(dst_dir_att)
try:
if not os.path.exists(dst_att):
print("Storing attachment : " + dst_att)
shutil.copyfile(src_att, dst_att)
except:
#LIB.debug_error()
meta = XML.xpath_node(all_docs, ".//document[.//*/@ref='"+ref+"']/_meta")
XML.add_error(meta, "__store_with_attachments()", "warning", "missing_file", "can't copy attachment, missing file", 0, src_att)
return path
def __build_index_section(base_url, all_docs, cat_ref, github_url, domain_refs):
"""
Build an HTML section for ref entity in all_docs.
"""
cat = XML.xpath_node(all_docs, (".//*[@ref='"+cat_ref+"']"))
cat_title = XML.xpath_plain(cat, "title/text()")
cat_about_html = XML.xpath_md(cat, "about/text()")
all_items = XML.xpath_list(all_docs, ".//*[@cat='"+cat_ref+"']")
rows = ""
for itm in all_items:
itm_ref = XML.xpath_plain(itm, "@ref")
if (not (itm_ref in domain_refs)) : continue
itm_icon = XML.xpath_plain(itm, "@icon")
doc = XML.xpath_node(itm, "ancestor::document")
itm_src_path = os.path.join(XML.xpath_plain(doc, "@dir"), XML.xpath_plain(doc, "@file"))
itm_ttl_html = XML.xpath_md(itm, "@title")
itm_about_html = XML.xpath_md(itm, "about/text()")
itm_src_url = __to_github(github_url, itm_src_path)
link_ref = __build_ref_link(base_url, all_docs, itm_ref)
rows += f"""
<tr>
<td class="icon"><img class="icon" alt="[icon]" src='{itm_ref}/{itm_icon}'/></td>
<td>{link_ref}</td>
<td>{itm_ttl_html}</td>
<td>(<a href="{itm_src_url}" target="_blank">Github</a>)</td>
</tr>\n
"""
ret = f"""
<div class="MenuContent">
<div id="primary">
<section class="comonSection singlefoliodetails">
<div class="container-fluid">
<div class="col-lg-12 noPadding">
<section class="col-md-10">
<div class="sectionTitle smTitle">
<h2>{cat_title} index</h2>
<div class="titleBar"></div>
</div>
<p>{cat_about_html}</p>
<table class="table table-bordered">
{rows}
</table>
</section>
</div>
</div>
</section>
</div>
</div>
"""
return __comment_html(ret)
def __build_content_attachments(base_url, all_docs, item):
"""
Build an HTML attached documents list for given ref.
"""
try:
root_doc = XML.xpath_node(item, "ancestor::document")
root_dir = XML.xpath_plain(root_doc, "@dir")
exts = "|".join([LIB.DOC_EXT[t] for t in ["txt","doc","slide","data"]])
attachments = XML.xpath_list(root_doc, "_meta/attachment[contains('"+exts+"', @ext)]")
inner_html = ""
for att in attachments:
att_path = XML.xpath_plain(att, "@to_path")
att_title = XML.xpath_plain(att, "@file")
att_ext = XML.xpath_plain(att, "@ext")
rel_path = os.path.relpath(att_path, start=root_dir)
link = f"""
<a title="{att_title}" href='{rel_path}' target="_blank" class="link_for_{att_ext}">{att_title}</a>
"""
inner_html += link
ret = f"""
<h2>Attached documents</h2>
<p>{inner_html}</p>
""" if inner_html > "" else ""
except:
ret = ""
return __comment_html(ret)
def __build_content_gallery(base_url, all_docs, item):
"""
Build an HTML image gallery for given ref.
"""
try:
root_doc = XML.xpath_node(item, "ancestor::document")
root_dir = XML.xpath_plain(root_doc, "@dir")
exts = LIB.DOC_EXT["img"]
images = XML.xpath_list(root_doc, "_meta/attachment[contains('"+exts+"', @ext)]")
inner_html = ""
for image in images:
img_path = XML.xpath_plain(image, "@to_path")
img_file = XML.xpath_plain(image, "@file")
rel_path = os.path.relpath(img_path, start=root_dir)
link = f"""
<span class="icon"><a title="{img_file}" href="{rel_path}"><img alt="[image]" src="{rel_path}"/></a></span>
"""
inner_html += link
ret = f"""
<h2>Image gallery</h2>
<p>{inner_html}</p>
""" if inner_html > "" else ""
except:
ret = ""
return __comment_html(ret)
def __build_content_text(base_url, all_docs, node, github_url, domain_cats):
"""
Build an HTML text
/!\ Links to refs broken by Markdown transformation NEED to replace refs in md with good
links BEFORE transformation.
"""
raw_content = "" #### XML.xpath_plain(node, "../raw_content/text()")
if raw_content > "" :
ref = XML.xpath_plain(node, "@ref")
doc = XML.xpath_node(node, "ancestor::document")
src_path = os.path.join(XML.xpath_plain(doc, "@dir"), XML.xpath_plain(doc, "@file"))
src_url = __to_github(github_url, src_path)
github = f"""<a href="{src_url}" target="_blank">Github</a>"""
md_html = MD.markdown(raw_content)
ret = f"""
<div class="sectionTitle smTitle">
<h6>{ref} ({github})</h6>
<div class="titleBar"></div>
</div>
{md_html}
"""
else:
ret = __build_content_chapter(base_url, all_docs, 2, node, github_url, domain_cats)
return ret
def __md_parse(xml_doc, text):
"""
Return the DOM from multiline markdown text. Headers (#..., ##..., ###...)
are interpreted as nodes name and the following text as the content of
these nodes.
/!\ plusieurs noeuds de même nom au même niveau ???
"""
lines = text.splitlines()
context = xml_doc
if LIB.sanitize(lines[0]) == "---": # Markdown with yaml meta-data block
yaml_block = ""
for i in range(1, len(lines)):
if LIB.sanitize(lines[i]) == "---": break
yaml_block += lines[i] + "\n"
meta_dict = yaml.load(yaml_block)
XML.add_dict_as_xml(context, meta_dict)
raw_content_text = ""
for j in range(i + 1, len(lines)):
raw_content_text += lines[j] + "\n"
node_raw = ET.SubElement(context, "raw_content")
node_raw.text = str(raw_content_text)
else: # Structured Markdown
cur_level = 0
code_fence_on = False
for i in range(len(lines)):
line = lines[i]
match_code_fence = re.match(r"^ *```", line)
if match_code_fence: code_fence_on = not code_fence_on
match_title = re.match(r"^ *(#+)(.+)", line)
if match_title and not code_fence_on:
new_level = len(match_title.group(1))
node_txt = match_title.group(2)
node_name = __extract_node_name(node_txt)
attributes = __extract_attributes(node_txt)
if new_level > cur_level + 1:
meta = XML.xpath_node(xml_doc, ".//_meta")
XML.add_error(meta, "__md_parse()", "fatal",
"md_level_mismatch", "level mismatch", i,
line)
else:
for lev in range(new_level, cur_level + 1):
context = context.getparent()
context = ET.SubElement(context, node_name, attributes)
cur_level = new_level
else:
context.text = (context.text
if context.text else "") + line + "\n"
node_raw = ET.SubElement(xml_doc, "raw_content")
node_raw.text = text
return xml_doc
def __update_refs(base_url, all_docs, text, node, domain_cats):
"""
Replace all Markdown link pattern [`CAT-xxxxxx`](../../interfaces/ITF-A_gnd) ) with correct url relative to base_url.
"""
#find all distinct ref patterns
refs = re.findall('\[`([A-Z]{2,6}-[\w_]+)`\]', text)
for ref in refs:
try:
itm = XML.xpath_node(all_docs, ".//*[@ref='"+ref+"']")
cat_ref = "CAT-" + itm.tag
if cat_ref in domain_cats:
url = base_url + cat_ref + "/" + ref + "/content.html"
else:
url=""
ttl = XML.xpath_plain(itm, "@title")
md_link = f"""[`{ref}`]({url} "{ttl}")"""
text = re.sub("\[`" + ref + "`\] *(\([^)]*\)|)", md_link, text)
except:
meta = XML.xpath_node(node, "ancestor::document/_meta")
XML.add_error(meta, "__update_refs()", "warning", "unknown_ref", "unknown reference", 0, ref)
return text
def __build_content_chapter(base_url, all_docs, level, node, github_url, domain_cats):
"""
Build recursively an HTML chapter at level for given node.
TODO : if level 2 produce :
<div class="sectionTitle smTitle">
<h2>configuration</h2>
<h6>CFG-sweeping_probe (<a href="https://github.com/Olivierff/PRJ-medtec_kit//tree/master/configurations/CFG-sweeping_probe" target="_blank">Github</a>)</h6>
<div class="titleBar"></div>
</div>
"""
try:
children = XML.xpath_list(node, "node()")
children_html = ""
for child in children:
if (ET.iselement(child)):
children_html += __build_content_chapter(base_url, all_docs, level+1, child, github_url, domain_cats)
else:
child = __update_refs(base_url, all_docs, child, node, domain_cats)
children_html += MD.markdown(child)
title = node.tag
if (level==2):
ref = XML.xpath_plain(node, "@ref")
doc = XML.xpath_node(node, "ancestor::document")
src_path = os.path.join(XML.xpath_plain(doc, "@dir"), XML.xpath_plain(doc, "@file"))
src_url = __to_github(github_url, src_path)
github = f"""<a href="{src_url}" target="_blank">Github</a>"""
ret = f"""
<div class="sectionTitle smTitle">
<h2>{title}</h2>
<h6>{ref} ({github})</h6>
<div class="titleBar"></div>
</div>
{children_html}
"""
else:
ret = f"""
<h{level}>{title}</h{level}>
{children_html}
"""
except:
ret = """
<p><strong>Error here !!! </strong></p>
"""
return ret
def __csv_parse(xml_doc, text):
"""
Return the DOM from csv text. Headers (#..., ##..., ###...)
are interpreted as nodes name and the columns text as the content of
these nodes.
"""
lines = text.splitlines()
reader = csv.reader(lines)
l = -1
for row in reader:
l += 1
if (l == 0):
header = row
elif (header[0].startswith("#")):
context = xml_doc
cur_level = 0
for i in range(len(header)):
ttl = header[i]
txt = row[i]
match_title = re.match(r" *(#+)(.+)", ttl)
if match_title:
new_level = len(match_title.group(1))
node_txt = match_title.group(2)
node_name = __extract_node_name(node_txt)
attributes = __extract_attributes(node_txt)
if new_level > cur_level + 1:
meta = XML.xpath_node(xml_doc, ".//_meta")
XML.add_error(meta, "__csv_parse()", "fatal",
"csv_level_mismatch", "level mismatch",
i, li)
else:
for lev in range(new_level, cur_level + 1):
context = context.getparent()
context = ET.SubElement(context, node_name, attributes)
cur_level = new_level
context.text = txt
else:
# not an error, not parsable as structured csv
#XML.add_error(meta, "__csv_parse()", "info", "csv_not_parsable", "not parsable header csv file", 0, header)
xml_doc.text = text
break
return xml_doc
def __build_ref_link(base_url, all_docs, ref):
"""
Build an HTML link for ref entity.
"""
try:
itm = XML.xpath_node(all_docs, ".//*[@ref='"+ref+"']")
cat_ref = "CAT-" + itm.tag
url = base_url + cat_ref + "/" + ref + "/content.html"
title = XML.xpath_plain(itm, "@title")
except:
url=""
title="Not found"
ret = f"""
<a href="{url}" title="{title}"><code>{ref}</code></a>
"""
return ret
def __build_content_section(base_url, all_docs, ref, github_url, domain_cats, domain_refs):
"""
Build an HTML section for ref entity in all_docs.
"""
try:
item = XML.xpath_node(all_docs, ".//*[@ref='"+ref+"']")
content = __build_content_text(base_url, all_docs, item, github_url, domain_cats)
gallery = __build_content_gallery(base_url, all_docs, item)
attachments = __build_content_attachments(base_url, all_docs, item)
crossref = __build_content_crossref(base_url, all_docs, ref, domain_refs)
ret = f"""
<div class="MenuContent">
<div id="primary">
<section class="comonSection singlefoliodetails">
<div class="container-fluid">
<div class="col-lg-12 noPadding">
<section class="col-md-10">
{content}
<hr/>
{gallery}
{attachments}
{crossref}
</section>
</div>
</div>
</section>
</div>
</div>
"""
except:
ret = """
<section class="col-md-10">
<h2>Unknown entity</h2>
<p>?!?</p>
</section>
"""
return __comment_html(ret)
def register_attachments(all_docs):
"""
register any attached "binary" document to its master document. Based on the file path
"""
attachments = XML.xpath_list(all_docs, "//document[count(*) <= 1]")
for att in attachments:
att_dir = XML.xpath_plain(att, "@dir")
att_path = XML.xpath_plain(att, "@path")
att_name = XML.xpath_plain(att, "@file")
att_ext = XML.xpath_plain(
att, "@ext"
) # vvvv Not very smart, but it's late and it works .... vvvv
root_pathes = XML.xpath_list(
all_docs,
"//document[count(*) > 1][@file='readme.md' or @file='Readme.md' or @file='README.md' or @file='readme.MD' or @file='Readme.MD' or @file='README.MD'][starts-with('"
+ att_dir + "', @dir)]/@path")
max_root_path = max(root_pathes, key=len, default="")
meta = XML.xpath_node(
all_docs, "//document[@path='" + max_root_path + "']/_meta")
XML.add_attachment(meta, att_path, att_ext, att_name)
return all_docs