• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
2#
3# Licensed under the Apache License, Version 2.0 (the "License");
4# you may not use this file except in compliance with the License.
5# You may obtain a copy of the License at
6#
7#     http://www.apache.org/licenses/LICENSE-2.0
8#
9# Unless required by applicable law or agreed to in writing, software
10# distributed under the License is distributed on an "AS IS" BASIS,
11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12# See the License for the specific language governing permissions and
13# limitations under the License.
14# ==============================================================================
15
16"""Library for operating on Python API Guide files."""
17
18from __future__ import absolute_import
19from __future__ import division
20from __future__ import print_function
21
22import os
23import re
24
25
26def md_files_in_dir(py_guide_src_dir):
27  """Returns a list of filename (full_path, base) pairs for guide files."""
28  all_in_dir = [(os.path.join(py_guide_src_dir, f), f)
29                for f in os.listdir(py_guide_src_dir)]
30  return [(full, f) for full, f in all_in_dir
31          if os.path.isfile(full) and f.endswith('.md')]
32
33
34class PyGuideParser(object):
35  """Simple parsing of a guide .md file.
36
37  Descendants can override the process_*() functions (called by process())
38  to either record information from the guide, or call replace_line()
39  to affect the return value of process().
40  """
41
42  def __init__(self):
43    self._lines = None
44
45  def process(self, full_path):
46    """Read and process the file at `full_path`."""
47    with open(full_path, 'rb') as f:
48      md_string = f.read().decode('utf-8')
49    self._lines = md_string.split('\n')
50    seen = set()
51
52    in_blockquote = False
53    for i, line in enumerate(self._lines):
54      if '```' in line:
55        in_blockquote = not in_blockquote
56
57      if not in_blockquote and line.startswith('# '):
58        self.process_title(i, line[2:])
59      elif not in_blockquote and line.startswith('## '):
60        section_title = line.strip()[3:]
61        existing_tag = re.search(' {([^}]+)} *$', line)
62        if existing_tag:
63          tag = existing_tag.group(1)
64        else:
65          tag = re.sub('[^a-zA-Z0-9]+', '_', section_title)
66          if tag in seen:
67            suffix = 0
68            while True:
69              candidate = '%s_%d' % (tag, suffix)
70              if candidate not in seen:
71                tag = candidate
72                break
73        seen.add(tag)
74        self.process_section(i, section_title, tag)
75
76      elif in_blockquote:
77        self.process_in_blockquote(i, line)
78      else:
79        self.process_line(i, line)
80
81    ret = '\n'.join(self._lines)
82    self._lines = None
83    return ret
84
85  def replace_line(self, line_number, line):
86    """Replace the contents of line numbered `line_number` with `line`."""
87    self._lines[line_number] = line
88
89  def process_title(self, line_number, title):
90    pass
91
92  def process_section(self, line_number, section_title, tag):
93    pass
94
95  def process_in_blockquote(self, line_number, line):
96    pass
97
98  def process_line(self, line_number, line):
99    pass
100