File: paragraph.py

package info (click to toggle)
fbless 0.2.3-7
  • links: PTS, VCS
  • area: main
  • in suites: experimental
  • size: 520 kB
  • sloc: python: 1,726; makefile: 8
file content (311 lines) | stat: -rw-r--r-- 10,423 bytes parent folder | download | duplicates (3)
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
# -*- mode: python; coding: utf-8; -*-

import sys
import locale

from .hyphenation import Hyphenation
from .options import styles, general

default_charset = locale.getdefaultlocale()[1]
hyph = Hyphenation()


def replace(s):
    """ Здесь происходит замена символов, если требуется
        u'\\u2013' -> '--'
        u'\\u2014' -> '---'
        u'\xa0'   -> неразрывный пробел
        u'\\u2026' -> dots...
        u'\xab'   -> '<<'
        u'\xbb'   -> '>>'
        u'\\u201c' -> ``
        u'\\u201d' -> ''
        u'\\u201e' -> ,,
        u'\xad'   -> мягкий перенос

        Правда, параметры метода .replace(), почему-то иные стоят.
    """
    return (s
        .replace('\u2013', '-')
        .replace('\u2014', '-')
        .replace('\xa0', ' ')
        .replace('\u2026', '...')
        #.replace(u'\xab', u'<<')
        #.replace(u'\xbb', u'>>')
        .replace('\xab', '"')
        .replace('\xbb', '"')
        .replace('\u201c', '"')
        .replace('\u201d', '"')
        .replace('\u201e', '"')
        .replace('\u2116', 'No')
        .replace('\xad', '')
        .replace('\u2019', '\'')
    )


class Attr:
    keys = {
        'newline': -1,
        'normal': 0,
        'strong': 1,
        'emphasis': 2,
        'a': 3,
        'style': 4,
        #
        'left_spaces': 10,
        #
        'search': 20,
        'cancel_search': 21,
    }

    def __init__(self):
        self.__dict__.update(self.keys)

    def __getitem__(self, name):
        return self.keys[name]

attr = Attr()


class Paragraph:
    def __init__(self, type='p', data='', attrs=[], lang=None,
                 id=None, byte_index=0):
        #print 'attrs:', attrs
        self.type = type
        self.data = data
        self.attrs = attrs
        self.search_offsets = []
        self.id = id
        self.lines = []
        self.lang = lang
        self.byte_index = byte_index
        if lang is None:
            self.lang = 'ru'
        try:
            self.__dict__.update(styles[type])
        except KeyError:
            self.__dict__.update(styles['default'])
        if self.justify == 'fill':
            self.stretch = True
        else:
            self.stretch = False

        self._first_indent = 0

        #self.maxlen = self.scr_cols-self.left_indent-self.right_indent

    def stretch_string(self, words, max_len):
        if len(words) < 2:
            return words
        len_words = len([i for i in words if i == ' ']) + 1
        sum_words = sum(len(i) for i in words
                        if not isinstance(i, (int, tuple)))

        # Avoid failing on division by zero.
        if len_words == 1:
            return words 

        min_space, long_space_num = divmod(max_len - sum_words, len_words - 1)
        short_space_num = len_words - long_space_num - 1
        bres = short_space_num / 2
        s = []
        for w in words:
            if w == ' ':
                if bres > 0:
                    bres -= long_space_num
                    s.append(' ' * (min_space + 1))
                else:
                    bres += short_space_num
                    s.append(' ' * (min_space + 2))
            else:
                s.append(w)
        return s

    def strip_line(self, line):
        # remove trailing whitespaces
        while line:
            if line[-1] == ' ' or isinstance(line[-1], (int, tuple)):
                line.pop()
            else:
                break

    def split_string(self):
        if self.lines:
            return  # already splitted
        if self.data == '\n':
            self.lines = ['']
            return

        if general['columns']:
            max_len = general['columns'] - self.left_indent - self.right_indent
        else:
            max_len = self.scr_cols - self.left_indent - self.right_indent

        offsets = []
        prev_offset = 0
        for attr_begin, attr_end, attr_type in self.attrs:
            offsets.append((prev_offset, attr.normal))
            offsets.append((attr_begin, attr_type))
            prev_offset = attr_end
        offsets.append((prev_offset, attr.normal))
        offsets.append((len(self.data), attr.normal))
        for begin, end in self.search_offsets:
            offsets.append((begin, attr.search))
            offsets.append((end, attr.cancel_search))
        offsets.sort()                  # sort by offsets

        #print offsets

        first_line_offset = self.first_line_indent
        words = [' ' * (self.first_line_indent - 1)]
        last_line = []

        line = []
        line.append(' ' * self.first_line_indent)
        line_len = self.first_line_indent
        attr_begin, cur_attr_type = offsets[0]
        line.append(cur_attr_type)
        in_search = False
        for attr_end, next_attr_type in offsets[1:]:
            data = self.data[attr_begin:attr_end]

            if data:
                if general['replace_chars']:
                    data = replace(data)

                if data.startswith(' '):
                    line.append(' ')
                    line_len += 1

                words = data.split()
                for word in words:
                    if line_len + len(word) + 1 > max_len:
                        if self.hyphenate:
                            # hyphenation
                            wl = hyph.hyphenate(word, self.lang)
                            for ww in wl:
                                if line_len + len(ww) + 1 <= max_len:
                                    line.append(ww + '-')
                                    word = word[len(ww):]
                                    if word.startswith('-'):
                                        word = word[1:]
                                    break
                        # remove trailing whitespaces
                        while line:
                            if line[-1] == ' ' or \
                                   isinstance(line[-1], (int, tuple)):
                                line.pop()
                            else:
                                break
                        line.append(attr.newline)
                        line.append(cur_attr_type)
                        if in_search:
                            line.append(attr.search)
                        line_len = 0

                    line.append(word)
                    line.append(' ')
                    line_len += len(word) + 1

                if not data.endswith(' ') and line:
                    line.pop()
                    line_len -= 1

            attr_begin = attr_end
            if next_attr_type == attr.search:
                in_search = True
            elif next_attr_type == attr.cancel_search:
                in_search = False
            else:
                cur_attr_type = next_attr_type
            line.append(next_attr_type)

        lines = []
        ln = []
        for w in line:
            if w == attr.newline:
                if self.stretch:
                    ln = self.stretch_string(ln, max_len)
                lines.append(ln)
                ln = []
            else:
                ln.append(w)
        if ln:
            lines.append(ln)

        for ln in lines:
            # add leading spaces
            if self.justify == 'center':
                len_line = sum(len(s) for s in ln
                               if not isinstance(s, (int, tuple)))
                d = (max_len - len_line) / 2
                spaces = ' ' * int(self.left_indent + d)
            elif self.justify == 'right':
                len_line = sum(len(s) for s in ln
                               if not isinstance(s, (int, tuple)))
                d = max_len - len_line
                spaces = ' ' * int(self.left_indent + d)
            else:  # left or fill
                spaces = ' ' * int(self.left_indent)

            if general['center_text']:
                # to center text, we pad it with spaces from the left
                padding = self.scr_cols - max_len
                padding -= self.left_indent + self.right_indent
                padding /= 2
                padding = ' ' * padding
                spaces += padding

            ln.insert(0, attr.left_spaces)
            ln.insert(1, spaces)

        self.lines = lines


if __name__ == '__main__':
    s = str(
        'Давно было готово заглавие, использующее титул замечательной '
        'монографии :вана Аксенова "Пикассо и окрестности". Предрешен '
        'был и тот свободный жанр "филологического романа", в котором '
        'написана моя любимая русская проза - от мандельштамовского '
        '"Разговора о Данте" до "Прогулок с Пушкиным" Синявского. Но '
        'что особенно важно, сама собой сформулировалась центральная '
        'тема - исповедь последнего советского поколения, голосом '
        'которого стал Сергей Довлатов.'
    )
    par = Paragraph(data=s, attrs=[(6, 10, attr.strong),
                                 (100, 240, attr.strong)])
    par.scr_cols = 48
    par.search_offsets = [(0, 50), (78, 120)]
    par.split_string()
    for l in par.lines:
        if 0:
            print(l)
        elif 0:
            for w in l:
                if w == ' ':
                    print('<sp>')
                else:
                    print(w)
        else:
            for w in l:
                if isinstance(w, int):
                    sys.stdout.write('<%d>' % w)
                    pass
                elif isinstance(w, tuple):
                    sys.stdout.write('<|>')
                else:
                    #print w,
                    #sys.stdout.write('|')
                    sys.stdout.write(w.encode('utf-8', 'replace'))
            print()
    print('~' * (par.scr_cols - par.right_indent))

    #par.print_str()
##     for s in par.lines:
##         if isinstance(s, int):
##             print '>', s, '<'
##         else:
##             for w in s:
##                 print w,
##             print