micke
/
gemtext2html
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Add docstrings and convert to package

Browse Source
master
Micke Nordin 3 years ago
parent aecbe362ad
commit eee0377a95
Signed by: micke
GPG Key ID: 014B273D614BE877
2 changed files with 129 additions and 68 deletions
Show Stats Download Patch File Download Diff File

5
.idea/.gitignore vendored
Unescape View File

@ -1,5 +0,0 @@
# Default ignored files
/shelf/
/workspace.xml
/.idea/
/.vscode/

192
src/convert.py → src/convert/__init__.py
Unescape View File

@ -1,32 +1,117 @@
#!/usr/bin/env python3
"""This is a python module that will parse gemtext and convert it to html5
"""
# -*- coding: utf-8 -*-
import sys
class State:
INITIAL = 0
TEXT = 1
LINK = 2
PRETEXT = 3
HEADING = 4
UNORDERED = 5
QUOTE = 6
class Tag:
LINK = '=>'
PRE = '```'
HEADING = '#'
UNORDERED = '*'
QUOTE = '>'
class GemParser:
"""This is the main parser class
"""
def __init__(self):
"""Constructor for the GemParser class
"""
self.mstate = State.INITIAL
self.recurse = False
def get_document_from_gemfile(self, filename):
"""This subroutine will read a file line by line and convert it to html
Args:
filename (str): A file name corresponing to a file of gemtext
Returns:
str: A valid html5 document as string
"""
rdocument = '<!DOCTYPE html>\n<html>\n<head>\n'
rdocument += '<title>gemtext2html</title>\n</head>\n<body>\n'
with open(filename) as gemtext:
mline: str = gemtext.readline()
while mline:
rline = self.parse_line(mline)
if rline is not None and rline != str() and rline != '\n':
rdocument += rline
mline = gemtext.readline()
rdocument += '{}</body>\n</html>\n'.format(self.get_end_tag())
return rdocument
def get_end_tag(self):
"""A subroutine that will emit the correct end tag for the state
Returns:
str: A html end tag
"""
tag = list()
tag.append('')
tag.append('</p>\n')
tag.append('</a>\n')
tag.append('</pre>\n')
tag.append('</h{}>\n')
tag.append('</ul>\n')
tag.append('</blockquote>\n')
return tag[self.mstate]
def get_start_tag(self):
"""A subroutine to emit the correct html start tag for the state
Returns:
str: A html start tag
"""
tag = list()
tag.append('')
tag.append('<p>\n')
tag.append('<a href="{}">')
tag.append('<pre{}>\n')
tag.append('<h{}>')
tag.append('<ul>\n')
tag.append('<blockquote>\n')
return tag[self.mstate]
def is_text(self, line):
"""A function that will check if this is a paragraph of text
Args:
line (str): A line of gemtext
Returns:
bool: True if it is text, False if it is something else
"""
return (not (line == '' or line == '\n')
and self.mstate == State.INITIAL and
(not line.startswith(Tag.LINK) and not line.startswith(Tag.PRE)
and not line.startswith(Tag.HEADING)
and not line.startswith(Tag.UNORDERED)
and not line.startswith(Tag.QUOTE)))
def parse_heading(self, line, level=0):
"""A function that will recursively call it self to get the correct
heading level
Args:
line (str): A gemtext heading line
level (int, optional): The heading level to start from. Defaults to 0.
Returns:
str: A html heading tag of the correct level
"""
if line.startswith(Tag.HEADING):
return self.parse_heading(line[1:], level + 1)
else:
return "{}{}{}".format(self.get_start_tag().format(level),
line.strip().rstrip('\n'),
self.get_end_tag().format(level))
def parse_line(self, line):
"""This subroutine will parse a single line of gemtext and enter the
correct state and output the corresponding html
Args:
line (string): A string of gemtext
Returns:
str: A string of html
"""
rstring = str()
is_text = self.is_text(line)
starts_with_pre = line.startswith(Tag.PRE)
@ -114,6 +199,14 @@ class GemParser:
sys.exit(1)
def parse_link(self, line):
"""This function will parse a gemtext link
Args:
line (str): A link line of gemtext
Returns:
str: A html fragment with a <a> tag
"""
linearr = line[2:].strip().split(' ')
link = linearr[0]
anchor = str().join(linearr[1:])
@ -124,54 +217,27 @@ class GemParser:
rline += self.get_end_tag()
return rline
def is_text(self, line):
return (not (line == '' or line == '\n')
and self.mstate == State.INITIAL and
(not line.startswith(Tag.LINK) and not line.startswith(Tag.PRE)
and not line.startswith(Tag.HEADING)
and not line.startswith(Tag.UNORDERED)
and not line.startswith(Tag.QUOTE)))
def get_start_tag(self):
tag = list()
tag.append('')
tag.append('<p>\n')
tag.append('<a href="{}">')
tag.append('<pre{}>\n')
tag.append('<h{}>')
tag.append('<ul>\n')
tag.append('<blockquote>\n')
return tag[self.mstate]
def get_end_tag(self):
tag = list()
tag.append('')
tag.append('</p>\n')
tag.append('</a>\n')
tag.append('</pre>\n')
tag.append('</h{}>\n')
tag.append('</ul>\n')
tag.append('</blockquote>\n')
return tag[self.mstate]
class State:
"""This is an enumeration of the states of the state machine
"""
INITIAL = 0
TEXT = 1
LINK = 2
PRETEXT = 3
HEADING = 4
UNORDERED = 5
QUOTE = 6
def get_document_from_gemfile(self, filename):
rdocument = '<!DOCTYPE html>\n<html>\n<head>\n<title>gemtext2html</title>\n</head>\n<body>\n'
with open(filename) as gemtext:
mline: str = gemtext.readline()
while mline:
rline = self.parse_line(mline)
if rline is not None and rline != str() and rline != '\n':
rdocument += rline
mline = gemtext.readline()
rdocument += '{}</body>\n</html>\n'.format(self.get_end_tag())
return rdocument
def parse_heading(self, line, level=0):
if line.startswith(Tag.HEADING):
return self.parse_heading(line[1:], level + 1)
else:
return "{}{}{}".format(self.get_start_tag().format(level), line.strip().rstrip('\n'),
self.get_end_tag().format(level))
class Tag:
"""This is an enumeration of the possible gemtext tags
"""
LINK = '=>'
PRE = '```'
HEADING = '#'
UNORDERED = '*'
QUOTE = '>'
if __name__ == '__main__':
Write Preview
Loading…
Cancel
Save