def handle_body(self, body_text):
"""Handle body.
Argument:
body_text: text string of one blog entry.
"""
if body_text:
body_text = convert.convert_hyperlink(body_text)
timestamp, categories, title = convert.get_metadata(
body_text.split('\n', 1)[0])
entry_body = convert.extract_entry_body(body_text)
rested_body = self.hatena2rest(entry_body)
return title, timestamp, categories, rested_body
def hatena2rest(self, str_body):
"""Convert body text of day entry to rest format.
Argument:
string: convert target string.
"""
footnotes = ''
table = []
tables = []
merge_string = ''
def parse_begin_ref(string_line):
"""Parse begining of reference block
Argument:
string: convert target string.
"""
pat_start_ref, match_obj = utils.regex_search(
'^>((http|https)://(.+?)|)>$', string_line)
if match_obj:
self.ref_flag = True
if match_obj.group(1):
repl_str = match_obj.group(1)
else:
repl_str = ''
string_line = pat_start_ref.sub(
repl_str,
string_line)
return string_line
def parse_end_ref(string_line):
"""Parse ending of reference block
Argument:
string: convert target string.
"""
pat_end_ref, match_obj = utils.regex_search(
'^<<', string_line)
if match_obj:
string_line = pat_end_ref.sub('\n\n', string_line)
self.ref_flag = False
else:
string_line = re.sub('^', ' ', string_line)
return string_line
def parse_begin_codeblock(string_line):
"""Parse begining of code block
Argument:
string: convert target string.
"""
pat_code_open, match_obj = utils.regex_search(
'>\|([a-zA-Z0-9]*)\|$|>\|()$', string_line)
if match_obj:
# code block opening
self.code_flag = True
if match_obj.group(1):
lexer_str = convert.replace_lexer(match_obj.group(1))
string_line = pat_code_open.sub(
'\n.. code-block:: ' + lexer_str + '\n',
string_line)
else:
string_line = pat_code_open.sub(
'\n.. code-block:: sh\n', string_line)
return string_line
def parse_end_codeblock(string_line):
"""Parse ending of codeblock.
Argument:
string_line: parsing target string.
"""
pat_code_close, match_obj = utils.regex_search(
'^\|\|<|^\|<$', string_line)
if match_obj:
string_line = pat_code_close.sub('\n', string_line)
# code block closing
self.code_flag = False
else:
string_line = re.sub('^', ' ', string_line)
return string_line
def extract_tables(string_line, table, tables):
"""Extract tables
Argument:
string_line: parsing target string.
table: parsing target table
tables: parsing target tables
"""
pat_table, match_obj = utils.regex_search(
'^\|(.+?)\|$', string_line)
if match_obj:
row_data = (match_obj.group(0),
match_obj.groups()[0].split('|'))
if not self.table_flag:
# table start
self.table_flag = True
table.append(row_data)
else:
if self.table_flag:
# table close
tables.append(table)
table = []
self.table_flag = False
return table, tables
if str_body:
# str_line exclude '\n'
for str_line in str_body.split('\n'):
# convert hyperlink
str_line = convert.convert_hyperlink(str_line)
# handle line inside code block
if self.code_flag:
str_line = parse_end_codeblock(str_line)
# handle line outside code block
else:
str_line = parse_begin_codeblock(str_line)
# replace '*' to '\*' of inline
str_line = convert.replace_asterisk(str_line)
# listing
str_line = self.listing2rest(str_line)
# convert shell var
str_line = convert.replace_shell_variable(str_line)
# section , subsection
str_line = convert.section2rest(str_line)
# convert image from hatena fotolife
str_line = self.fotolife2rest(str_line)
# convert footnote
str_line, footnotes_ = convert.footnote2rest(str_line)
if footnotes_:
footnotes += footnotes_ + '\n'
# convert refs
if self.ref_flag:
str_line = parse_end_ref(str_line)
else:
str_line = parse_begin_ref(str_line)
# extract table data
table, tables = extract_tables(str_line, table, tables)
# remove internal_link and convert blog parts
str_line = self.convert_blog_parts(str_line)
merge_string += utils.remove_element_entity(str_line) + '\n'
# convert table
merge_string = self.table2rest(tables, merge_string)
self.code_flag = False
return merge_string + '\n' + footnotes
