refactor and linting (680ab594) · Commits · CTI Tools / tosca2doc

src/doc2tosca.py

+123 −72

Original line number	Original line	Diff line number	Diff line
	@@ -35,6 +35,14 @@ imports:

	'''		'''

			sections_to_models = {
			6: 'vnfd',
			7: 'nsd',
			8: 'pnfd',
			9: 'common'
			}


	SUBSECTIONS = [		SUBSECTIONS = [
	"Artifact Types",		"Artifact Types",
	"Data Types",		"Data Types",
	@@ -51,6 +59,7 @@ SUBSECTIONS = [
	MODELS = {}		MODELS = {}
	EXAMPLES = {}		EXAMPLES = {}


	class Section():		class Section():
	'''		'''
	Defines a section of the base document		Defines a section of the base document
	@@ -72,15 +81,23 @@ class Section():

	def __repr__(self):		def __repr__(self):
	if self.is_annex:		if self.is_annex:
	return "({}, Annex {}, {}-{})".format(self.title,self.letter, self.from_id, self.to_id)		return "({}, Annex {}, {}-{})".format(
	return "({}, {}, {}-{})".format(self.title, self.number, self.from_id, self.to_id)		self.title, self.letter, self.from_id, self.to_id
			)
			return "({}, {}, {}-{})".format(
			self.title, self.number, self.from_id, self.to_id
			)


	def match_definition_incipit(txt):		def match_definition_incipit(txt):
	'''		'''
	Returns tru if txt matches the incipit of a definition,		Returns tru if txt matches the incipit of a definition,
	identified by the word 'tosca'		identified by the word 'tosca'
	'''		'''
	return bool(re.match(r'^tosca\.[a-zA-Z\.:0-9\s]*$',txt.split("\n")[0].strip()))		return bool(
			re.match(r'^tosca\.[a-zA-Z\.:0-9\s]*$', txt.split("\n")[0].strip())
			)


	def is_tosca_def(table):		def is_tosca_def(table):
	'''		'''
	@@ -94,6 +111,7 @@ def is_tosca_def(table):
	len(table.columns) == 1 and \		len(table.columns) == 1 and \
	match_definition_incipit(txt)		match_definition_incipit(txt)


	def tosca_model_info(name, version, imports):		def tosca_model_info(name, version, imports):
	'''		'''
	Returns a dictionary to hold information on the model		Returns a dictionary to hold information on the model
	@@ -106,6 +124,7 @@ def tosca_model_info(name, version, imports):
	'buf': StringIO()		'buf': StringIO()
	}		}


	def get_content(doc):		def get_content(doc):
	'''		'''
	Returns a list of all paragraphs and tables in the Document		Returns a list of all paragraphs and tables in the Document
	@@ -127,6 +146,7 @@ def get_content(doc):
	print("Tables: " + str(table_count))		print("Tables: " + str(table_count))
	return ret		return ret


	def find_sect(sect_to_find, start_idx, doc_content):		def find_sect(sect_to_find, start_idx, doc_content):
	'''		'''
	Returns the index in the doc_content list to the first paragraph		Returns the index in the doc_content list to the first paragraph
	@@ -135,13 +155,15 @@ def find_sect(sect_to_find, start_idx, doc_content):
	'''		'''
	while start_idx < len(doc_content):		while start_idx < len(doc_content):
	my_elem = doc_content[start_idx]		my_elem = doc_content[start_idx]
	if isinstance(my_elem, Paragraph) and my_elem.text.strip() == sect_to_find:		if isinstance(my_elem, Paragraph) and \
			my_elem.text.strip() == sect_to_find:
	break		break
	start_idx = start_idx + 1		start_idx = start_idx + 1

	print("FOUND " + sect_to_find + " at " + str(start_idx))		print("FOUND " + sect_to_find + " at " + str(start_idx))
	return start_idx		return start_idx


	def is_lvl2_section_hdn(txt):		def is_lvl2_section_hdn(txt):
	''' Returns true if txt is level 2 heading'''		''' Returns true if txt is level 2 heading'''
	clean_txt = txt.strip()		clean_txt = txt.strip()
	@@ -153,12 +175,14 @@ def is_lvl2_section_hdn(txt):

	return subtitle in SUBSECTIONS		return subtitle in SUBSECTIONS


	def is_lvl1_section_hdn(txt):		def is_lvl1_section_hdn(txt):
	''' Returns true if txt is level 1 heading'''		''' Returns true if txt is level 1 heading'''
	clean_txt = txt.strip()		clean_txt = txt.strip()
	return bool(re.match(r'^[0-9]+\t[a-zA-Z\s]*$', clean_txt)) or \		return bool(re.match(r'^[0-9]+\t[a-zA-Z\s]*$', clean_txt)) or \
	bool(re.match(r'^Annex[\s][A-Z]+[\s\t]+[a-zA-Z\s]', clean_txt))		bool(re.match(r'^Annex[\s][A-Z]+[\s\t]+[a-zA-Z\s]', clean_txt))


	def find_all_sections(doc_content):		def find_all_sections(doc_content):
	'''		'''
	Scans the body of the document to find level 1 sections		Scans the body of the document to find level 1 sections
	@@ -171,17 +195,26 @@ def find_all_sections(doc_content):

	while end_indx < len(doc_content):		while end_indx < len(doc_content):
	my_elem = doc_content[end_indx]		my_elem = doc_content[end_indx]
	if isinstance(my_elem, Paragraph) and is_lvl1_section_hdn(my_elem.text):		if isinstance(my_elem, Paragraph) and \
			is_lvl1_section_hdn(my_elem.text):
	if start_indx != 0:		if start_indx != 0:
	sections.append(Section(start_indx, end_indx-1, doc_content[start_indx].text))		sections.append(
			Section(
			start_indx,
			end_indx-1,
			doc_content[start_indx].text)
			)

	start_indx = end_indx		start_indx = end_indx

	end_indx = end_indx + 1		end_indx = end_indx + 1

	sections.append(Section(start_indx, end_indx-1, doc_content[start_indx].text))		sections.append(
			Section(start_indx, end_indx-1, doc_content[start_indx].text)
			)
	return sections		return sections


	def write_subsection_to_file(txt, buf):		def write_subsection_to_file(txt, buf):
	'''		'''
	Writes a subsection header in utf-8 encoding to file buf		Writes a subsection header in utf-8 encoding to file buf
	@@ -191,6 +224,7 @@ def write_subsection_to_file(txt, buf):
	buf.write('\n')		buf.write('\n')
	buf.write('\n')		buf.write('\n')


	def write_table_to_file(tab, buf):		def write_table_to_file(tab, buf):
	'''		'''
	Writes content of table t in utf-8 encoding to file F		Writes content of table t in utf-8 encoding to file F
	@@ -201,6 +235,10 @@ def write_table_to_file(tab, buf):
	buf.write('\n')		buf.write('\n')
	buf.write('\n')		buf.write('\n')


			range_err_mess = "ERR: Out of range (A: {}, B: {}, IDX: {}, LEN(CONTENT): {})"


	def gen_tables_btwn(a_id, b_id, content, buf):		def gen_tables_btwn(a_id, b_id, content, buf):
	'''		'''
	Loops over content and writes all tosca definitions to the		Loops over content and writes all tosca definitions to the
	@@ -211,13 +249,14 @@ def gen_tables_btwn(a_id, b_id, content, buf):
	for idx in range(a_id, b_id):		for idx in range(a_id, b_id):

	if idx >= len(content):		if idx >= len(content):
	print("ERROR: Paragraph out of range (A: {}, B: {}, IDX: {}, LEN(CONTENT): {})".format(		print(
	a_id, b_id,idx, len(content)))		range_err_mess.format(a_id, b_id, idx, len(content)))
	return definitions_count		return definitions_count

	tmp_elem = content[idx]		tmp_elem = content[idx]

	if isinstance(tmp_elem, Paragraph) and is_lvl2_section_hdn(tmp_elem.text):		if isinstance(tmp_elem, Paragraph) and \
			is_lvl2_section_hdn(tmp_elem.text):
	print(tmp_elem.text)		print(tmp_elem.text)
	write_subsection_to_file(tmp_elem.text.split("\t")[1], buf)		write_subsection_to_file(tmp_elem.text.split("\t")[1], buf)
	definitions_count = definitions_count + 1		definitions_count = definitions_count + 1
	@@ -228,11 +267,13 @@ def gen_tables_btwn(a_id, b_id, content, buf):

	elif isinstance(tmp_elem, Table):		elif isinstance(tmp_elem, Table):
	txt = tmp_elem.rows[0].cells[0].text		txt = tmp_elem.rows[0].cells[0].text
	if txt.strip().startswith("Name") or txt.strip().startswith("Shorthand") or \		if txt.strip().startswith("Name") or \
			txt.strip().startswith("Shorthand") or \
	txt.strip().startswith("tosca_def"):		txt.strip().startswith("tosca_def"):
	continue		continue
	return definitions_count		return definitions_count


	def generate_header(		def generate_header(
	model_name,		model_name,
	buf,		buf,
	@@ -248,34 +289,23 @@ def generate_header(
	spec_version=spec_version,		spec_version=spec_version,
	imports=imports))		imports=imports))

	def generate_templates(
	filename,
	spec_ver=SPEC_VERSION,
	yaml_root='uri',
	tosc_ver=DEFAULT_TOSCA_VERSION):
	'''
	Takes a filename or file object and loads the definition into the MODELS dictionary
	'''
	if isinstance(filename, str):
	print("Opening " + filename)

	for mod in MODEL_NAMES:		def init_models(yaml_root, spec_ver, tosc_ver):
			for model in MODEL_NAMES:
	import_stmt = 'etsi_nfv_sol001_common_types.yaml'		import_stmt = 'etsi_nfv_sol001_common_types.yaml'

	if yaml_root != 'local':		if yaml_root != 'local':
	import_stmt = \		import_stmt = \
	'https://forge.etsi.org/rep/nfv/SOL001/raw/{}/'.format(spec_ver) + import_stmt		'https://forge.etsi.org/rep/nfv/SOL001/raw/{}/{}'.format(
	MODELS[mod] = tosca_model_info(		spec_ver, import_stmt
	mod,		)

			MODELS[model] = tosca_model_info(
			model,
	spec_ver,		spec_ver,
	'- ' + import_stmt		'- ' + import_stmt
	)		)

	try:
	sol_001 = docx.Document(filename)
	except:
	print("Error opening the submitted Docx file")
	raise ValueError("Cannot open the submitted Docx file")

	for mod in MODELS:		for mod in MODELS:
	generate_header(		generate_header(
	MODELS[mod]['name'],		MODELS[mod]['name'],
	@@ -285,27 +315,47 @@ def generate_templates(
	tosc_ver		tosc_ver
	)		)


			def generate_templates(
			filename,
			spec_ver=SPEC_VERSION,
			yaml_root='uri',
			tosc_ver=DEFAULT_TOSCA_VERSION):
			'''
			Takes a filename or file object and loads the definition into
			the MODELS dictionary
			'''
			if isinstance(filename, str):
			print("Opening " + filename)

			init_models(yaml_root, spec_ver, tosc_ver)

			try:
			sol_001 = docx.Document(filename)
			except:
			print("Error opening the submitted Docx file")
			raise ValueError("Cannot open the submitted Docx file")

	content = get_content(sol_001)		content = get_content(sol_001)
	sections = find_all_sections(content)		sections = find_all_sections(content)

	sections_to_models = {
	6 : 'vnfd',
	7 : 'nsd',
	8 : 'pnfd',
	9 : 'common'
	}

	for sect in sections:		for sect in sections:

	if not sect.is_annex:		if not sect.is_annex:
	if sect.number in sections_to_models.keys():		if sect.number in sections_to_models.keys():
	model = sections_to_models[sect.number]		model = sections_to_models[sect.number]
	count = gen_tables_btwn(sect.from_id, sect.to_id, content, MODELS[model]['buf'])		count = gen_tables_btwn(
			sect.from_id, sect.to_id, content, MODELS[model]['buf']
			)
	print("Printed " + str(count) + " types to " + model)		print("Printed " + str(count) + " types to " + model)
	else:		else:
	if sect.letter == "A":		if sect.letter == "A" or sect.letter == "E":
	count = generate_examples_between(sect.from_id, sect.to_id, content, EXAMPLES)		count = generate_examples_between(
	print("Printed " + str(count) + " types to " + "Annex " + sect.letter)		sect.from_id, sect.to_id, content, EXAMPLES
			)
			print("Printed {} types to Annex {}".format(
			str(count), sect.letter)
			)


	def print_to_files(prefix=None):		def print_to_files(prefix=None):
	@@ -335,6 +385,7 @@ def print_to_files(prefix=None):
	newf.write("\n")		newf.write("\n")
	newf.close()		newf.close()


	def parse_version_from_filename(filename):		def parse_version_from_filename(filename):
	'''		'''
	Parses the version from the filename		Parses the version from the filename
	@@ -349,9 +400,11 @@ def parse_version_from_filename(filename):
	.replace("0", ".").strip(".").strip("p.docx")		.replace("0", ".").strip(".").strip("p.docx")
	return ""		return ""


	def slugify(t):		def slugify(t):
	return t.replace(" ", "_").lower()		return t.replace(" ", "_").lower()


	if __name__ == "__main__":		if __name__ == "__main__":

	try:		try:
	@@ -365,5 +418,3 @@ if __name__ == "__main__":
	generate_templates(SOL001_FN, spec_ver=ver)		generate_templates(SOL001_FN, spec_ver=ver)

	print_to_files()		print_to_files()