Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1# Copyright 2016 Grist Labs, Inc.
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.
15import bisect
16import re
17from typing import Dict, List, Tuple
19_line_start_re = re.compile(r'^', re.M)
21class LineNumbers(object):
22 """
23 Class to convert between character offsets in a text string, and pairs (line, column) of 1-based
24 line and 0-based column numbers, as used by tokens and AST nodes.
26 This class expects unicode for input and stores positions in unicode. But it supports
27 translating to and from utf8 offsets, which are used by ast parsing.
28 """
29 def __init__(self, text):
30 # type: (str) -> None
31 # A list of character offsets of each line's first character.
32 self._line_offsets = [m.start(0) for m in _line_start_re.finditer(text)]
33 self._text = text
34 self._text_len = len(text)
35 self._utf8_offset_cache = {} # type: Dict[int, List[int]] # maps line num to list of char offset for each byte in line
37 def from_utf8_col(self, line, utf8_column):
38 # type: (int, int) -> int
39 """
40 Given a 1-based line number and 0-based utf8 column, returns a 0-based unicode column.
41 """
42 offsets = self._utf8_offset_cache.get(line)
43 if offsets is None:
44 end_offset = self._line_offsets[line] if line < len(self._line_offsets) else self._text_len
45 line_text = self._text[self._line_offsets[line - 1] : end_offset]
47 offsets = [i for i,c in enumerate(line_text) for byte in c.encode('utf8')]
48 offsets.append(len(line_text))
49 self._utf8_offset_cache[line] = offsets
51 return offsets[max(0, min(len(offsets)-1, utf8_column))]
53 def line_to_offset(self, line, column):
54 # type: (int, int) -> int
55 """
56 Converts 1-based line number and 0-based column to 0-based character offset into text.
57 """
58 line -= 1
59 if line >= len(self._line_offsets):
60 return self._text_len
61 elif line < 0:
62 return 0
63 else:
64 return min(self._line_offsets[line] + max(0, column), self._text_len)
66 def offset_to_line(self, offset):
67 # type: (int) -> Tuple[int, int]
68 """
69 Converts 0-based character offset to pair (line, col) of 1-based line and 0-based column
70 numbers.
71 """
72 offset = max(0, min(self._text_len, offset))
73 line_index = bisect.bisect_right(self._line_offsets, offset) - 1
74 return (line_index + 1, offset - self._line_offsets[line_index])