aboutsummaryrefslogtreecommitdiff
path: root/mammoth/writers/markdown.py
blob: d355ff3cad2c851acb9b870cfed3de0d567ce793 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
from __future__ import unicode_literals

import re


class _WriterOutput(object):
    def __init__(self, start, end, anchor_position=None):
        self.start = start
        self.end = end
        self.anchor_position = anchor_position


class _MarkdownState(object):
    def __init__(self):
        self.list_state = _MarkdownListState()


class _MarkdownListState(object):
    def __init__(self):
        self.count = 0


def _symmetric_wrapped(end):
    return _Wrapped(end, end)


class _Wrapped(object):
    def __init__(self, start, end):
        self._start = start
        self._end = end
    
    def __call__(self, attributes, markdown_state):
        return _WriterOutput(self._start, self._end)


def _hyperlink(attributes, markdown_state):
    href = attributes.get("href", "")
    if href:
        return _WriterOutput(
            "[", "]({0})".format(href),
            anchor_position="before",
        )
    else:
        return _default_output


def _image(attributes, markdown_state):
    src = attributes.get("src", "")
    alt_text = attributes.get("alt", "")
    if src or alt_text:
        return _WriterOutput("![{0}]({1})".format(alt_text, src), "")
    else:
        return _default_output


def _list(ordered):
    def call(attributes, markdown_state):
        return _WriterOutput("", "\n")
    
    return call


def _list_item(attributes, markdown_state):
    list_state = markdown_state.list_state
    list_state.count += 1
    return _WriterOutput("{0}. ".format(list_state.count), "\n")


def _init_writers():
    writers = {
        "p": _Wrapped("", "\n\n"),
        "br": _Wrapped("", "  \n"),
        "strong": _symmetric_wrapped("__"),
        "em": _symmetric_wrapped("*"),
        "a": _hyperlink,
        "img": _image,
        "ol": _list(ordered=True),
        "li": _list_item,
    }
    
    for level in range(1, 7):
        writers["h{0}".format(level)] = _Wrapped("#" * level + " ", "\n\n")
    
    return writers


_writers = _init_writers()
_default_output = _WriterOutput("", "")
_default_writer = lambda attributes, markdown_state: _default_output


class MarkdownWriter(object):
    def __init__(self):
        self._fragments = []
        self._element_stack = []
        self._markdown_state = _MarkdownState()
    
    def text(self, text):
        self._fragments.append(_escape_markdown(text))
    
    def start(self, name, attributes=None):
        if attributes is None:
            attributes = {}
        
        output = _writers.get(name, _default_writer)(attributes, self._markdown_state)
        
        anchor_before_start = output.anchor_position == "before"
        if anchor_before_start:
            self._write_anchor(attributes)
        
        self._fragments.append(output.start)
        
        if not anchor_before_start:
            self._write_anchor(attributes)
        
        self._element_stack.append(output.end)

    def end(self, name):
        end = self._element_stack.pop()
        self._fragments.append(end)
    
    def self_closing(self, name, attributes=None):
        self.start(name, attributes)
        self.end(name)
    
    def append(self, other):
        self._fragments.append(other)
    
    def as_string(self):
        return "".join(self._fragments)
    
    def _write_anchor(self, attributes):
        html_id = attributes.get("id")
        if html_id:
            self._fragments.append('<a id="{0}"></a>'.format(html_id))


def _escape_markdown(value):
    return re.sub(r"([\`\*_\{\}\[\]\(\)\#\+\-\.\!])", r"\\\1", re.sub("\\\\", "\\\\\\\\", value))