| 1 |
# |
| 2 |
# Create and extract text from ODF, handling whitespace correctly. |
| 3 |
# Copyright (C) 2008 J. David Eisenberg |
| 4 |
# |
| 5 |
# This program is free software; you can redistribute it and/or modify |
| 6 |
# it under the terms of the GNU General Public License as published by |
| 7 |
# the Free Software Foundation; either version 2 of the License, or |
| 8 |
# (at your option) any later version. |
| 9 |
# |
| 10 |
# This program is distributed in the hope that it will be useful, |
| 11 |
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 |
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 13 |
# GNU General Public License for more details. |
| 14 |
# |
| 15 |
# You should have received a copy of the GNU General Public License along |
| 16 |
# with this program; if not, write to the Free Software Foundation, Inc., |
| 17 |
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. |
| 18 |
|
| 19 |
|
| 20 |
""" |
| 21 |
Class for handling whitespace properly in OpenDocument. |
| 22 |
|
| 23 |
While it is possible to use getTextContent() and setTextContent() |
| 24 |
to extract or create ODF content, these won't extract or create |
| 25 |
the appropriate <text:s>, <text:tab>, or <text:line-break> |
| 26 |
elements. This module takes care of that problem. |
| 27 |
""" |
| 28 |
|
| 29 |
from .element import Node |
| 30 |
from .text import LineBreak, S, Tab |
| 31 |
|
| 32 |
|
| 33 |
class WhitespaceText: |
| 34 |
def __init__(self): |
| 35 |
self.textBuffer = [] |
| 36 |
self.spaceCount = 0 |
| 37 |
|
| 38 |
def addTextToElement(self, odfElement, s): |
| 39 |
"""Process an input string, inserting |
| 40 |
<text:tab> elements for '\t', |
| 41 |
<text:line-break> elements for '\n', and |
| 42 |
<text:s> elements for runs of more than one blank. |
| 43 |
These will be added to the given element. |
| 44 |
""" |
| 45 |
i = 0 |
| 46 |
ch = ' ' |
| 47 |
|
| 48 |
# When we encounter a tab or newline, we can immediately |
| 49 |
# dump any accumulated text and then emit the appropriate |
| 50 |
# ODF element. |
| 51 |
# |
| 52 |
# When we encounter a space, we add it to the text buffer, |
| 53 |
# and then collect more spaces. If there are more spaces |
| 54 |
# after the first one, we dump the text buffer and then |
| 55 |
# then emit the appropriate <text:s> element. |
| 56 |
|
| 57 |
while i < len(s): |
| 58 |
ch = s[i] |
| 59 |
if ch == '\t': |
| 60 |
self._emitTextBuffer(odfElement) |
| 61 |
odfElement.addElement(Tab()) |
| 62 |
i += 1 |
| 63 |
elif ch == '\n': |
| 64 |
self._emitTextBuffer(odfElement) |
| 65 |
odfElement.addElement(LineBreak()) |
| 66 |
i += 1 |
| 67 |
elif ch == ' ': |
| 68 |
self.textBuffer.append(' ') |
| 69 |
i += 1 |
| 70 |
self.spaceCount = 0 |
| 71 |
while i < len(s) and (s[i] == ' '): |
| 72 |
self.spaceCount += 1 |
| 73 |
i += 1 |
| 74 |
if self.spaceCount > 0: |
| 75 |
self._emitTextBuffer(odfElement) |
| 76 |
self._emitSpaces(odfElement) |
| 77 |
else: |
| 78 |
self.textBuffer.append(ch) |
| 79 |
i += 1 |
| 80 |
|
| 81 |
self._emitTextBuffer(odfElement) |
| 82 |
|
| 83 |
def _emitTextBuffer(self, odfElement): |
| 84 |
"""Creates a Text Node whose contents are the current textBuffer. |
| 85 |
Side effect: clears the text buffer. |
| 86 |
""" |
| 87 |
if len(self.textBuffer) > 0: |
| 88 |
odfElement.addText(''.join(self.textBuffer)) |
| 89 |
self.textBuffer = [] |
| 90 |
|
| 91 |
def _emitSpaces(self, odfElement): |
| 92 |
"""Creates a <text:s> element for the current spaceCount. |
| 93 |
Side effect: sets spaceCount back to zero |
| 94 |
""" |
| 95 |
if self.spaceCount > 0: |
| 96 |
spaceElement = S(c=self.spaceCount) |
| 97 |
odfElement.addElement(spaceElement) |
| 98 |
self.spaceCount = 0 |
| 99 |
|
| 100 |
|
| 101 |
def addTextToElement(odfElement, s): |
| 102 |
wst = WhitespaceText() |
| 103 |
wst.addTextToElement(odfElement, s) |
| 104 |
|
| 105 |
|
| 106 |
def extractText(odfElement): |
| 107 |
'''Extract text content from an Element, with whitespace represented |
| 108 |
properly. Returns the text, with tabs, spaces, and newlines |
| 109 |
correctly evaluated. This method recursively descends through the |
| 110 |
children of the given element, accumulating text and "unwrapping" |
| 111 |
<text:s>, <text:tab>, and <text:line-break> elements along the way. |
| 112 |
''' |
| 113 |
result = [] |
| 114 |
|
| 115 |
if len(odfElement.childNodes) != 0: |
| 116 |
for child in odfElement.childNodes: |
| 117 |
if child.nodeType == Node.TEXT_NODE: |
| 118 |
result.append(child.data) |
| 119 |
elif child.nodeType == Node.ELEMENT_NODE: |
| 120 |
subElement = child |
| 121 |
tagName = subElement.qname |
| 122 |
if tagName == ('urn:oasis:names:tc:opendocument:xmlns:text:1.0', 'line-break'): |
| 123 |
result.append('\n') |
| 124 |
elif tagName == ('urn:oasis:names:tc:opendocument:xmlns:text:1.0', 'tab'): |
| 125 |
result.append('\t') |
| 126 |
elif tagName == ('urn:oasis:names:tc:opendocument:xmlns:text:1.0', 's'): |
| 127 |
c = subElement.getAttribute('c') |
| 128 |
if c: |
| 129 |
spaceCount = int(c) |
| 130 |
else: |
| 131 |
spaceCount = 1 |
| 132 |
|
| 133 |
result.append(' ' * spaceCount) |
| 134 |
else: |
| 135 |
result.append(extractText(subElement)) |
| 136 |
return ''.join(result) |