wgroeneveld
/
dokuwiki-to-hugo
2
0
Fork 0
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

wiring everything together using a class decorator

master
wgroeneveld 2017-01-15 15:08:47 +01:00
parent 635e746756
commit aa00a107f0
9 changed files with 58 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/__init__.py Normal file
View File

@ -0,0 +1,2 @@
# this initializes the submodule __init__
from src.markdown import *

11
src/markdown/__init__.py Normal file
View File

@ -0,0 +1,11 @@
# https://docs.python.org/3/tutorial/modules.html
# you need to define __all__ to be able to let from x import * work...
# there is no out-of-the-box dynamic solution
# see http://stackoverflow.com/questions/1057431/loading-all-modules-in-a-folder-in-python
from os.path import dirname, basename, isfile
import glob
modules = glob.glob(dirname(__file__)+"/*.py")
__all__ = [ basename(f)[:-3] for f in modules if isfile(f) and not f.endswith('__init__.py')]
print('loaded markdown converters: ' + ', '.join(__all__))

4
src/markdown/code.py
View File

@ -1,6 +1,8 @@
from abc import ABC
from re import compile
from src.markdown_converter import MarkdownConverter
class BaseMarkdownCode(ABC):
markdown = "```"
@ -24,10 +26,12 @@ class BaseMarkdownCode(ABC):
result = result.replace(match[0], BaseMarkdownCode.markdown + language)
return result.replace('</' + self.tag + '>', BaseMarkdownCode.markdown)
@MarkdownConverter.Register
class MarkdownFile(BaseMarkdownCode):
def __init__(self):
super().__init__('file')
@MarkdownConverter.Register
class MarkdownCode(BaseMarkdownCode):
def __init__(self):
super().__init__('code')

7
src/markdown/headers.py
View File

@ -1,7 +1,10 @@
from collections import OrderedDict
from re import compile
class MarkdownHeader:
from src.markdown_converter import MarkdownConverter
@MarkdownConverter.Register
class MarkdownHeader():
pattern = compile('(=+)(.*?)(=+)')
head = "="
config = {

9
src/markdown/links.py
View File

@ -1,8 +1,11 @@
import os
from os import walk
import re
from os import walk
class MarkdownLinks:
from src.markdown_converter import MarkdownConverter
@MarkdownConverter.Register
class MarkdownLinks():
# see http://pythex.org/
pattern = re.compile('(\[\[)(.*?)(\]\])')

6
src/markdown/lists.py
View File

@ -1,6 +1,10 @@
import re
class MarkdownOrderedList:
from src.markdown_converter import MarkdownConverter
@MarkdownConverter.Register
class MarkdownOrderedList():
pattern = re.compile('(^-\s)(.*)', re.MULTILINE)
def convert(self, text):

11
src/markdown/simplestyle.py
View File

@ -1,6 +1,9 @@
from abc import ABC
from re import compile
from src.markdown_converter import MarkdownConverter
class NopStyle(ABC):
def convert(self, text):
return text
@ -29,27 +32,33 @@ class SimpleStyleBetweenTags(ABC):
result = result.replace(orig_header, new_header)
return result
@MarkdownConverter.Register
class MarkdownLineBreak(SimpleReplacementStyle):
def __init__(self):
super().__init__('<br/>', '\\')
# inline html is supported with Hugo, don't need the tags.
class MarkdownInlineHtml:
@MarkdownConverter.Register
class MarkdownInlineHtml():
def convert(self, text):
return text.replace('<html>', '').replace('</html>', '')
# bold in Doku is bold in MD
@MarkdownConverter.Register
class MarkdownBold(NopStyle):
pass
@MarkdownConverter.Register
class MarkdownItalic(SimpleStyleBetweenTags):
def __init__(self):
super().__init__('*', '//')
@MarkdownConverter.Register
class MarkdownStrikeThrough(SimpleStyleBetweenTags):
def __init__(self):
super().__init__('~~', '<del>', '</del>')
@MarkdownConverter.Register
class MarkdownInlineCode(SimpleStyleBetweenTags):
def __init__(self):
super().__init__('`', "''", "''")

38
src/markdown_converter.py
View File

@ -1,33 +1,19 @@
from functools import reduce
from src.markdown.links import MarkdownLinks
from src.markdown.headers import MarkdownHeader
from src.markdown.simplestyle import MarkdownItalic, MarkdownBold, MarkdownStrikeThrough
from pathlib import Path
class MarkdownConverter:
converters = []
@classmethod
def Register(cls, converter_class):
cls.converters.append(converter_class())
return converter_class
def __init__(self, file):
self.file = file
self.converters = (
# TODO auto-discover these. How do I do that, without interfaces?
MarkdownHeader(),
MarkdownLinks(),
MarkdownItalic(),
MarkdownBold(),
MarkdownStrikeThrough()
)
def convert(self):
converted = []
with open(self.file, 'r') as file:
for line in file:
converted.append(self.convert_line(line))
return "\n".join(converted)
def convert_line(self, line):
convertfns = map(lambda converter: converter.convert, self.converters)
massconvert = reduce(lambda red1, red2: lambda text: red1(red2(line)), convertfns, lambda text: text)
return massconvert(line)
text = Path(self.file).read_text()
# TODO solve this functional-style instead of mutating text
for converter in MarkdownConverter.converters:
text = converter.convert(text)
return text

6
test/expected_markdown_output.txt
View File

@ -1,7 +1,7 @@
# header 1
# header 1
##### header 5
##### header 5
[hi]({{< relref "hello world" >}}) this is a test!
{{< wp Dogs >}} are cool, look it up. [sublink]({{< relref "link/sub" >}} example.
{{< wp Dogs >}} are cool, look it up. [sublink]({{< relref "link/sub" >}}) example.