adjustments search and roundtrip SAREF4BLG (6a695e1e) · Commits · SAREF / saref-pypeline

src/saref_pypeline/constants.py

+2 −2

Original line number	Original line	Diff line number	Diff line
	@@ -84,5 +84,5 @@ owl:topObjectProperty a owl:ObjectProperty ;
	"""		"""
	)		)
	PATTERN_TERM_NAME = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9_-]+$")		PATTERN_TERM_NAME = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9_-]+$")
	CAPTION_TABLE_RE = re.compile(r"^\sTable[\s\xa0]+([A-Z0-9\.]+)[\xa0\s:](.)\s$")		CAPTION_TABLE_RE = re.compile(r"^\sTable[\s\xa0]+([A-Z0-9\.]+)[\xa0\s:]([\s\S]?)\s$")
	CAPTION_FIGURE_RE = re.compile(r"^\sFigure[\s\xa0]+([A-Z0-9\.]+)[\xa0\s:](.)\s$")		CAPTION_FIGURE_RE = re.compile(r"^\sFigure[\s\xa0]+([A-Z0-9\.]+)[\xa0\s:]([\s\S]?)\s$")

src/saref_pypeline/etsi.py

+3 −0

Original line number	Original line	Diff line number	Diff line
	@@ -208,6 +208,9 @@ class P_STYLE(StrEnum, metaclass=_MetaEnum):
	# Style found in SAREF4AUTO V1.1.1		# Style found in SAREF4AUTO V1.1.1
	List_Paragraph = "List Paragraph"		List_Paragraph = "List Paragraph"

			# Style found in SAREF4BLDG V2.1.1
			Annotation_Text = "annotation text"


	class C_STYLE(StrEnum, metaclass=_MetaEnum):		class C_STYLE(StrEnum, metaclass=_MetaEnum):
	"""ETSI Character Styles, obtained from skeleton"""		"""ETSI Character Styles, obtained from skeleton"""

src/saref_pypeline/pipeline.py

+1 −0

Original line number	Original line	Diff line number	Diff line
	@@ -1132,6 +1132,7 @@ class SAREFPipeline:
	return dumper.represent_str(data.name)		return dumper.represent_str(data.name)

	yaml.SafeDumper.add_representer(WK_FIELD, represent_string)		yaml.SafeDumper.add_representer(WK_FIELD, represent_string)
			os.makedirs(os.path.dirname(metadata_file), exist_ok=True)
	with open(metadata_file, "w") as f:		with open(metadata_file, "w") as f:
	yaml.safe_dump(self.projects_metadata, f)		yaml.safe_dump(self.projects_metadata, f)

src/saref_pypeline/ts/ts2md_extractor.py

+38 −5

Original line number	Original line	Diff line number	Diff line
	@@ -645,7 +645,9 @@ class TS2MDExtractor:
	):		):
	"""Reference, Example => use "tab" between "item/number" and "text"."""		"""Reference, Example => use "tab" between "item/number" and "text"."""
	md = self.extract_inner_content(paragraph)		md = self.extract_inner_content(paragraph)
	if md.startswith("EXAMPLE"):		if not md:
			return ""
			elif md.startswith("EXAMPLE"):
	# Example		# Example
	left, right = md.split("\t", 1)		left, right = md.split("\t", 1)
	content = right.replace("\n", "\n ")		content = right.replace("\n", "\n ")
	@@ -797,7 +799,8 @@ class TS2MDExtractor:
	):		):
	"""Programming language"""		"""Programming language"""
	md = self.extract_inner_content(paragraph, extract_format)		md = self.extract_inner_content(paragraph, extract_format)
	return f"```\n{md}\n```"		md = md.replace("&", "&").replace("<", "<")
			return f"""<pre><code class="language-turtle">{md}</code></pre>""" if md else ""

	def extract_EQ(		def extract_EQ(
	self, paragraph: Paragraph, extract_format: ExtractFormat = ExtractFormat.MD		self, paragraph: Paragraph, extract_format: ExtractFormat = ExtractFormat.MD
	@@ -830,7 +833,11 @@ class TS2MDExtractor:
	<figcaption>{label}: {caption}</figcaption>		<figcaption>{label}: {caption}</figcaption>
	</figure>\n"""		</figure>\n"""
	else:		else:
	return f"{md}"		pre_code = self.get_paragraph_pre_code(paragraph)
			return f"""<figure>
			{pre_code}
			<figcaption>{label}: {caption}</figcaption>
			</figure>\n"""

	def extract_FL(		def extract_FL(
	self, paragraph: Paragraph, extract_format: ExtractFormat = ExtractFormat.MD		self, paragraph: Paragraph, extract_format: ExtractFormat = ExtractFormat.MD
	@@ -997,6 +1004,24 @@ class TS2MDExtractor:
	image_paragraph = get_prev_block(self.document, paragraph)		image_paragraph = get_prev_block(self.document, paragraph)
	return self.get_paragraph_image_info(image_paragraph, i + 1)		return self.get_paragraph_image_info(image_paragraph, i + 1)

			def get_paragraph_pre_code(self, block, i: int = 0):
			"""
			If table with one row and one column, it contains turtle code.
			"""
			if i > 3:
			return ""
			if not isinstance(block, Table):
			block = get_prev_block(self.document, block)
			return self.get_paragraph_pre_code(block, i+1)
			if len(block.rows) != 1 or len(block.columns) != 1:
			logger.warning("expected table with one line and one column for Listings")
			return ""

			cell = block.cell(0, 0)
			ttl = "\n".join(p.text for p in cell.paragraphs)
			ttl = ttl.replace("&", "&").replace("<", "<")
			return f"""<pre><code class="language-turtle">{ttl}</code></pre>""" if ttl else ""

	def extract_table(self, table, extract_format: ExtractFormat = ExtractFormat.HTML):		def extract_table(self, table, extract_format: ExtractFormat = ExtractFormat.HTML):
	"""		"""
	Generate HTML for a python-docx Table.		Generate HTML for a python-docx Table.
	@@ -1007,6 +1032,10 @@ class TS2MDExtractor:
	"""		"""
	assert isinstance(table, Table)		assert isinstance(table, Table)

			# ignore if nrows=1 and ncols=1 like in SAREF4BLDG
			if len(table.rows) == 1 and len(table.columns)==1:
			return

	cap_id, cap_text = self.caption_from_prev_paragraph(table)		cap_id, cap_text = self.caption_from_prev_paragraph(table)

	if cap_text and "Prefixes and namespaces" in cap_text:		if cap_text and "Prefixes and namespaces" in cap_text:
	@@ -1118,6 +1147,10 @@ class TS2MDExtractor:
	else:		else:
	return ""		return ""

			def extract_Annotation_Text(
			self, paragraph: Paragraph, extract_format: ExtractFormat = ExtractFormat.MD
			):
			return self.extract_Normal(paragraph, extract_format)

	def print_admonition(classes: str, title: str, md: str):		def print_admonition(classes: str, title: str, md: str):
	prefix = 4 * " "		prefix = 4 * " "
	@@ -1126,7 +1159,7 @@ def print_admonition(classes: str, title: str, md: str):


	def get_prev_block(document: Document, target):		def get_prev_block(document: Document, target):
	"""Return the block (Paragraph or Table) that appears immediately before target_tbl."""		"""Return the block (Paragraph or Table) that appears immediately before target."""
	prev = None		prev = None
	for block in iter_block_items(document):		for block in iter_block_items(document):
	if isinstance(block, Table \| Paragraph) and block._element is target._element:		if isinstance(block, Table \| Paragraph) and block._element is target._element:

src/saref_pypeline/ts/ts_generator.py

+12 −3

Original line number	Original line	Diff line number	Diff line
	@@ -902,11 +902,11 @@ class TSGenerator:
	informative_soup = BeautifulSoup()		informative_soup = BeautifulSoup()
	normative_h2 = normative_soup.find("h2")		normative_h2 = normative_soup.find("h2")
	if normative_h2:		if normative_h2:
	informative_h3 = normative_h2.find_next("h2")		informative_h2 = normative_h2.find_next("h2")
	for el in informative_h3.find_next_siblings():		for el in informative_h2.find_next_siblings():
	el.extract()		el.extract()
	informative_soup.append(el)		informative_soup.append(el)
	for h2 in normative_soup.find_all("h2"):		for h2 in normative_soup.find_all(re.compile("h1\|h2")):
	h2.extract()		h2.extract()

	self.insert_references("Normative references", normative_soup)		self.insert_references("Normative references", normative_soup)
	@@ -1380,6 +1380,8 @@ class TSGenerator:
	if isinstance(child, Tag):		if isinstance(child, Tag):
	if child.name == "img":		if child.name == "img":
	self.insert_soup_img(child, text_width)		self.insert_soup_img(child, text_width)
			if child.name == "pre":
			self.insert_soup_pre(child)
	elif child.name == "figcaption":		elif child.name == "figcaption":
	self.insert_soup_figcaption(child)		self.insert_soup_figcaption(child)

	@@ -1463,6 +1465,13 @@ class TSGenerator:
	with Bookmark(self, id):		with Bookmark(self, id):
	self.insert_soup_children(el)		self.insert_soup_children(el)

			def insert_soup_pre(self, pre: Tag) -> None:
			if not (len(pre.contents) == 1 and pre.contents[0].name == "code"):
			logger.warning("Not supported <pre> element")
			code = pre.contents[0].text
			self.new_paragraph(code, style=P_STYLE.PL)


	def insert_soup_a(self, a: Tag) -> None:		def insert_soup_a(self, a: Tag) -> None:
	self.ensure_cursor_paragraph()		self.ensure_cursor_paragraph()
	if href := a.get("href"):		if href := a.get("href"):