def extract_code_blocks(self, entry, style):
code_blocks = data_structures.TPM2_Partx_File()
style_nr = int(re.search("([0-9]+)", style).group(1))
cont = ExtractionNavigator.selector(entry)
while cont:
# if the current entry is a text:p, table:table, or test:list with the current style,
# append it to code blocks
if isinstance(entry, Tag) and entry.name == constants.XML_TEXT_P:
element = data_structures.TPM2_Partx_CommentLine(
entry.get_text())
code_blocks.append(element) # once
elif isinstance(entry,
Tag) and entry.name == constants.XML_TABLE_TABLE:
table_rows = []
rows = entry.find_all(constants.XML_TABLE_TABLE_ROW)
for i in range(0, len(rows)):
r = []
cells = rows[i].find_all(constants.XML_TABLE_TABLE_CELL)
for cell in cells:
r.append(cell.get_text())
table_rows.append(r)
element = data_structures.TPM2_Partx_Table(
"", "", 0, table_rows)
code_blocks.append(element) # once
elif isinstance(entry, Tag) and entry.name == constants.XML_TEXT_LIST\
and entry.has_attr(constants.XML_TEXT_STYLE_NAME) \
and entry[constants.XML_TEXT_STYLE_NAME] == style:
text_ps = entry.findAll(constants.XML_TEXT_P)
for text_p in text_ps:
if not isinstance(text_p, Tag):
break
utils.convert_indentation(text_p)
text_p_text = text_p.get_text()
element = data_structures.TPM2_Partx_CodeLine(text_p_text)
code_blocks.append(element) # for every code line
# add an empty line for readability
element = data_structures.TPM2_Partx_CodeLine("")
code_blocks.append(element) # once
next_list = entry
current_style_nr = style_nr
cont = False
while current_style_nr - style_nr < 2 or current_style_nr - style_nr > 4:
if next_list:
next_list = next_list.next_sibling.next_sibling
else:
break
if next_list and next_list.has_attr(
constants.XML_TEXT_STYLE_NAME):
current_style = next_list[constants.XML_TEXT_STYLE_NAME]
result = re.search("WWNum([0-9]+)", current_style)
if result and int(result.group(1)) > style_nr:
current_style_nr = int(result.group(1))
if current_style == style:
cont = True
break
entry = entry.next_sibling.next_sibling
return code_blocks
def extract_code_blocks(self, entry, style):
code_blocks = data_structures.TPM2_Partx_File()
style_nr = int(re.search("([0-9]+)", style).group(1))
cont = ExtractionNavigator.selector(entry)
while cont:
# if the current entry is a text:p, table:table, or test:list with the current style,
# append it to code blocks
if isinstance(entry, Tag) and entry.name == constants.XML_TEXT_P:
element = data_structures.TPM2_Partx_CommentLine(entry.get_text())
code_blocks.append(element) # once
elif isinstance(entry, Tag) and entry.name == constants.XML_TABLE_TABLE:
table_rows = []
rows = entry.find_all(constants.XML_TABLE_TABLE_ROW)
for i in range(0,len(rows)):
r = []
cells = rows[i].find_all(constants.XML_TABLE_TABLE_CELL)
for cell in cells:
r.append(cell.get_text())
table_rows.append(r)
element = data_structures.TPM2_Partx_Table("","", 0, table_rows)
code_blocks.append(element) # once
elif isinstance(entry, Tag) and entry.name == constants.XML_TEXT_LIST\
and entry.has_attr(constants.XML_TEXT_STYLE_NAME) \
and entry[constants.XML_TEXT_STYLE_NAME] == style:
text_ps = entry.findAll(constants.XML_TEXT_P)
for text_p in text_ps:
if not isinstance(text_p, Tag):
break
utils.convert_indentation(text_p)
text_p_text = text_p.get_text()
element = data_structures.TPM2_Partx_CodeLine(text_p_text)
code_blocks.append(element) # for every code line
# add an empty line for readability
element = data_structures.TPM2_Partx_CodeLine("")
code_blocks.append(element) # once
next_list = entry
current_style_nr = style_nr
cont = False
while current_style_nr - style_nr < 2 or current_style_nr - style_nr > 4:
if next_list:
next_list = next_list.next_sibling.next_sibling
else:
break
if next_list and next_list.has_attr(constants.XML_TEXT_STYLE_NAME):
current_style = next_list[constants.XML_TEXT_STYLE_NAME]
result = re.search("WWNum([0-9]+)", current_style)
if result and int(result.group(1)) > style_nr:
current_style_nr = int(result.group(1))
if current_style == style:
cont = True
break
entry = entry.next_sibling.next_sibling
return code_blocks
def extract_tpm2_part3_command(self, function, style):
command = data_structures.TPM2_Partx_File()
entry = self.next_entry(function)
""" distinguish between a text:list and a text:p tag:
In case the tag is of type: text:list simply use its text:style-name as
condition for further iteration (to find futher lines of the code).
In case the tag is of type text:p, use its siblings text:style-name --
assuming its next_sibling is of type text:list.
"""
# extract the style
if entry.name == constants.XML_TEXT_LIST:
style = entry[constants.XML_TEXT_STYLE_NAME]
if entry.name == constants.XML_TEXT_P:
style = entry.next_sibling.next_sibling[
constants.XML_TEXT_STYLE_NAME]
# entry tag is of type text:list, text:p or table:table
continue_extraction = self.selector(entry)
while continue_extraction:
if entry.name == constants.XML_TEXT_P:
element = data_structures.TPM2_Partx_CommentLine(
entry.get_text())
command.append(element) # once
elif entry.name == constants.XML_TABLE_TABLE:
table_rows = []
rows = entry.find_all(constants.XML_TABLE_TABLE_ROW)
for i in range(0, len(rows)):
r = []
cells = rows[i].find_all(constants.XML_TABLE_TABLE_CELL)
for cell in cells:
r.append(cell.get_text())
table_rows.append(r)
element = data_structures.TPM2_Partx_Table(
"", "", 0, table_rows)
command.append(element) # once
elif entry.name == constants.XML_TEXT_LIST:
text_ps = entry.findAll(constants.XML_TEXT_P)
for text_p in text_ps:
if not isinstance(text_p, Tag):
break
utils.convert_indentation(text_p)
text_p_text = text_p.get_text()
element = data_structures.TPM2_Partx_CodeLine(text_p_text)
command.append(element) # for every code line
command.append(data_structures.TPM2_Partx_CodeLine(""))
entry = entry.find_next(self.selector)
if not isinstance(entry, Tag):
continue_extraction = False
continue
if entry.name == constants.XML_TEXT_P:
continue_extraction = True
elif entry.name == constants.XML_TEXT_LIST:
continue_extraction = (
entry[constants.XML_TEXT_STYLE_NAME] == style)
elif entry.name == constants.XML_TABLE_TABLE:
next_list = entry.find_next(constants.XML_TEXT_LIST)
continue_extraction = (
next_list[constants.XML_TEXT_STYLE_NAME] == style)
else:
continue_extraction = False
return command