File: common.py

package info (click to toggle)
opencc 1.2.0%2Bds1-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 4,260 kB
  • sloc: cpp: 5,181; python: 470; makefile: 126; javascript: 106; sh: 70
file content (226 lines) | stat: -rw-r--r-- 7,210 bytes parent folder | download
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
# -*- coding: utf-8 -*-

import codecs
import sys


def sort_items(input_filename, output_filename):
    input_file = codecs.open(input_filename, "r", encoding="utf-8")

    lines = [line.rstrip("\r\n") for line in input_file]
    input_file.close()

    def line_type(line):
        if line == "" or line.strip() == "":
            return "empty"
        if line.startswith("#"):
            return "comment"
        if "\t" in line:
            return "entry"
        raise ValueError("Invalid dictionary line: " + line)

    parsed = []
    for line in lines:
        parsed.append({"type": line_type(line), "content": line})

    entry_lines = [i for i, p in enumerate(parsed) if p["type"] == "entry"]
    if not entry_lines:
        header_blocks = []
        current = []
        for p in parsed:
            if p["type"] == "comment":
                current.append(p["content"])
            elif p["type"] == "empty":
                if current:
                    header_blocks.append(list(current))
                    current = []
        if current:
            header_blocks.append(list(current))

        output_file = open(output_filename, "wb")
        for idx, block in enumerate(header_blocks):
            for line in block:
                output_file.write((line + "\n").encode("utf-8"))
            if idx < len(header_blocks) - 1:
                output_file.write(b"\n")
        if header_blocks:
            output_file.write(b"\n")
        output_file.close()
        return

    first_entry = entry_lines[0]
    last_entry = entry_lines[-1]

    header_end = -1
    for i in range(first_entry - 1, -1, -1):
        if parsed[i]["type"] == "empty":
            header_end = i
            break

    header_blocks = []
    current = []
    for i in range(0, header_end + 1):
        if parsed[i]["type"] == "comment":
            current.append(parsed[i]["content"])
        elif parsed[i]["type"] == "empty":
            if current:
                header_blocks.append(list(current))
                current = []
    if current:
        header_blocks.append(list(current))

    footer_blocks = []
    current = []
    for i in range(last_entry + 1, len(parsed)):
        if parsed[i]["type"] == "comment":
            current.append(parsed[i]["content"])
        elif parsed[i]["type"] == "empty":
            if current:
                footer_blocks.append(list(current))
                current = []
    if current:
        footer_blocks.append(list(current))

    annotated_entries = []
    floating_blocks = []
    current = []
    entry_index = 0
    for i in range(header_end + 1, last_entry + 1):
        p = parsed[i]
        if p["type"] == "comment":
            current.append(p["content"])
            continue
        if p["type"] == "empty":
            if current:
                floating_blocks.append({"anchor": entry_index, "lines": list(current)})
                current = []
            continue
        if p["type"] == "entry":
            attached = None
            if current:
                has_empty = False
                for j in range(i - 1, -1, -1):
                    if parsed[j]["type"] == "entry":
                        break
                    if parsed[j]["type"] == "empty":
                        has_empty = True
                        break
                if has_empty:
                    floating_blocks.append({"anchor": entry_index, "lines": list(current)})
                else:
                    attached = list(current)
                current = []

            key, value = p["content"].split("\t", 1)
            annotated_entries.append(
                {
                    "key": key,
                    "value": value,
                    "attached": attached,
                    "original_index": entry_index,
                }
            )
            entry_index += 1

    if current:
        floating_blocks.append({"anchor": entry_index, "lines": list(current)})

    annotated_entries.sort(key=lambda e: e["key"])
    index_map = {e["original_index"]: i for i, e in enumerate(annotated_entries)}
    for block in floating_blocks:
        if block["anchor"] in index_map:
            block["anchor"] = index_map[block["anchor"]]
        else:
            block["anchor"] = len(annotated_entries)

    floating_by_anchor = {}
    for block in floating_blocks:
        floating_by_anchor.setdefault(block["anchor"], []).append(block["lines"])

    output_file = open(output_filename, "wb")

    for idx, block in enumerate(header_blocks):
        for line in block:
            output_file.write((line + "\n").encode("utf-8"))
        if idx < len(header_blocks) - 1:
            output_file.write(b"\n")
    if header_blocks and annotated_entries:
        output_file.write(b"\n")

    for i, entry in enumerate(annotated_entries):
        for block in floating_by_anchor.get(i, []):
            output_file.write(b"\n")
            for line in block:
                output_file.write((line + "\n").encode("utf-8"))
            output_file.write(b"\n")

        if entry["attached"]:
            for line in entry["attached"]:
                output_file.write((line + "\n").encode("utf-8"))
        output_file.write(
            (entry["key"] + "\t" + entry["value"] + "\n").encode("utf-8")
        )

    for block in floating_by_anchor.get(len(annotated_entries), []):
        output_file.write(b"\n")
        for line in block:
            output_file.write((line + "\n").encode("utf-8"))

    if footer_blocks:
        if annotated_entries:
            output_file.write(b"\n")
        for idx, block in enumerate(footer_blocks):
            for line in block:
                output_file.write((line + "\n").encode("utf-8"))
            if idx < len(footer_blocks) - 1:
                output_file.write(b"\n")

    output_file.close()


def reverse_items(input_filename, output_filename):
    input_file = codecs.open(input_filename, "r", encoding="utf-8")
    dic = {}

    for line in input_file:
        stripped = line.strip()
        if not stripped or stripped.startswith("#"):
            continue
        key, value = line.split("\t")
        while value[-1] == "\n" or value[-1] == "\r":
            value = value[:-1]

        value_list = value.split(" ")
        for value in value_list:
            if value in dic:
                dic[value].append(key)
            else:
                dic[value] = [key]

    input_file.close()

    output_file = open(output_filename, "wb")

    for key in sorted(dic.keys()):
        line = key + "\t" + " ".join(dic[key]) + "\n"
        output_file.write(line.encode('utf-8'))

    output_file.close()


def find_target_items(input_filename, keyword):
    input_file = codecs.open(input_filename, "r", encoding="utf-8")
    for line in input_file:
        stripped = line.strip()
        if not stripped or stripped.startswith("#"):
            continue
        key, value = line.split("\t")
        while value[-1] == "\n" or value[-1] == "\r":
            value = value[:-1]

        value_list = value.split(" ")
        for value in value_list:
            if keyword in value:
                sys.stdout.write(line)

    input_file.close()