summaryrefslogtreecommitdiffstats
path: root/vendor/unicode-script/scripts/unicode.py
blob: e40a92c6df43cf6c4196ce182e3cb23f3e9c8820 (plain)
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
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
#!/usr/bin/env python
#
# Copyright 2011-2015 The Rust Project Developers. See the COPYRIGHT
# file at the top-level directory of this distribution and at
# http://rust-lang.org/COPYRIGHT.
#
# Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
# http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
# <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
# option. This file may not be copied, modified, or distributed
# except according to those terms.

# This script uses the following Unicode tables:
# - PropertyValueAliases.txt
# - ScriptExtensions.txt
# - Scripts.txt
#
# Since this should not require frequent updates, we just store this
# out-of-line and check the unicode.rs file into git.

import fileinput, re, os, sys

preamble = '''// Copyright 2012-2018 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

// NOTE: The following code was generated by "scripts/unicode.py", do not edit directly

#![allow(missing_docs, non_upper_case_globals, non_snake_case)]

pub use tables_impl::*;

#[rustfmt::skip]
mod tables_impl {
use crate::ScriptExtension;
'''

# Close `mod impl {`
ending='''
}
'''

UNICODE_VERSION = (13, 0, 0)

UNICODE_VERSION_NUMBER = "%s.%s.%s" %UNICODE_VERSION

def escape_char(c):
    return "'\\u{%x}'" % c

def fetch(f):
    if not os.path.exists(os.path.basename(f)):
        if "emoji" in f:
            os.system("curl -O https://www.unicode.org/Public/emoji/%s.%s/%s"
                      % (UNICODE_VERSION[0], UNICODE_VERSION[1], f))
        else:
            os.system("curl -O http://www.unicode.org/Public/%s/ucd/%s"
                      % (UNICODE_VERSION_NUMBER, f))

    if not os.path.exists(os.path.basename(f)):
        sys.stderr.write("cannot load %s" % f)
        exit(1)

def group_cats(cats):
    cats_out = {}
    for cat in cats:
        cats_out[cat] = group_cat(cats[cat])
    return cats_out

def aliases():
    """
    Fetch the shorthand aliases for each longhand Script name
    """
    fetch("PropertyValueAliases.txt")
    longforms = {}
    shortforms = {}
    re1 = re.compile(r"^ *sc *; *(\w+) *; *(\w+)")
    for line in fileinput.input(os.path.basename("PropertyValueAliases.txt")):
        m = re1.match(line)
        if m:
            l = m.group(2).strip()
            s = m.group(1).strip()
            assert(s not in longforms)
            assert(l not in shortforms)
            longforms[s] = l
            shortforms[l] = s
        else:
            continue

    return (longforms, shortforms)

def format_table_content(f, content, indent):
    line = " "*indent
    first = True
    for chunk in content.split(","):
        if len(line) + len(chunk) < 98:
            if first:
                line += chunk
            else:
                line += ", " + chunk
            first = False
        else:
            f.write(line + ",\n")
            line = " "*indent + chunk
    f.write(line)

# Implementation from unicode-segmentation
def load_properties(f, interestingprops):
    fetch(f)
    props = {}
    # Note: these regexes are different from those in unicode-segmentation,
    # becase we need to handle spaces here
    re1 = re.compile(r"^ *([0-9A-F]+) *; *([^#]+) *#")
    re2 = re.compile(r"^ *([0-9A-F]+)\.\.([0-9A-F]+) *; *([^#]+) *#")

    for line in fileinput.input(os.path.basename(f)):
        prop = None
        d_lo = 0
        d_hi = 0
        m = re1.match(line)
        if m:
            d_lo = m.group(1)
            d_hi = m.group(1)
            prop = m.group(2).strip()
        else:
            m = re2.match(line)
            if m:
                d_lo = m.group(1)
                d_hi = m.group(2)
                prop = m.group(3).strip()
            else:
                continue
        if interestingprops and prop not in interestingprops:
            continue
        d_lo = int(d_lo, 16)
        d_hi = int(d_hi, 16)
        if prop not in props:
            props[prop] = []
        props[prop].append((d_lo, d_hi))

    return props

# Implementation from unicode-segmentation
def emit_table(f, name, t_data, t_type = "&'static [(char, char)]", is_pub=True,
        pfun=lambda x: "(%s,%s)" % (escape_char(x[0]), escape_char(x[1])), is_const=True):
    pub_string = "const"
    if not is_const:
        pub_string = "let"
    if is_pub:
        pub_string = "pub " + pub_string
    f.write("    %s %s: %s = &[\n" % (pub_string, name, t_type))
    data = ""
    first = True
    for dat in t_data:
        if not first:
            data += ","
        first = False
        data += pfun(dat)
    format_table_content(f, data, 8)
    f.write("\n    ];\n\n")

def emit_search(f):
    f.write("""
pub fn bsearch_range_value_table<T: Copy>(c: char, r: &'static [(char, char, T)]) -> Option<T> {
    use core::cmp::Ordering::{Equal, Less, Greater};
    match r.binary_search_by(|&(lo, hi, _)| {
        if lo <= c && c <= hi { Equal }
        else if hi < c { Less }
        else { Greater }
    }) {
        Ok(idx) => {
            let (_, _, cat) = r[idx];
            Some(cat)
        }
        Err(_) => None
    }
}

#[inline]
pub fn get_script(c: char) -> Option<Script> {
    bsearch_range_value_table(c, SCRIPTS)
}

#[inline]
pub fn get_script_extension(c: char) -> Option<ScriptExtension> {
    bsearch_range_value_table(c, SCRIPT_EXTENSIONS)
}
""")

def emit_enums(f, script_list, extension_list, longforms):
    """
    Emit the Script and ScriptExtension enums as well as any related utility functions
    """

    f.write("""
#[derive(Clone, Copy, PartialEq, Eq, Debug, Hash)]
#[non_exhaustive]
#[allow(non_camel_case_types)]
#[repr(u8)]
/// A value of the `Script` property
pub enum Script {
    /// Unknown script
    Unknown = 0xFF,
    /// Zyyy
    Common = 0xFE,
    /// Zinh,
    Inherited = 0xFD,
""")
    for (i, script) in enumerate(script_list):
        f.write("    /// %s\n    %s = %s,\n" % (script, longforms[script], i))
    f.write("}\n")
    f.write("pub const NEXT_SCRIPT: u8 = %s;" % len(script_list))
    f.write("""

pub mod script_extensions {
    use crate::ScriptExtension;
    pub const COMMON: ScriptExtension = ScriptExtension::new_common();
    pub const INHERITED: ScriptExtension = ScriptExtension::new_inherited();
    pub const UNKNOWN: ScriptExtension = ScriptExtension::new_unknown();
""")
    for (i, script) in enumerate(script_list):
        first = 0
        second = 0
        third = 0
        # need to replace L because `hex()` will spit out an L suffix for larger numbers
        if i < 64:
            first = hex(1 << i).replace("L", "")
        elif i < 128:
            second = hex(1 << (i - 64)).replace("L", "")
        else:
            third = hex(1 << (i - 128)).replace("L", "")
        f.write("    /// %s\n    pub const %s: ScriptExtension = ScriptExtension::new(%s, %s, %s);\n" %
                (longforms[script], longforms[script].upper(), first, second, third))
        if script != longforms[script]:
            f.write("    /// %s\n    pub const %s: ScriptExtension = %s;\n" %
                    (longforms[script], script.upper(), longforms[script].upper()))
    for ext in extension_list:
        longform = ", ".join([longforms[s] for s in ext])
        name = "_".join([s.upper() for s in ext])
        expr = ext[0].upper()
        for e in ext[1:]:
            expr = "%s.union(%s)" % (expr, e.upper())
        f.write("    /// %s\n    pub const %s: ScriptExtension = %s;\n" % (longform, name, expr))
    f.write("""}

""")

    # Generate implementation for the `Script`
    generate_script_impl(f)


def generate_script_impl(f):
    """Generates an `impl Script { ... }` section with all the required functions"""

    # Open `impl Script` section.
    f.write("""impl Script {
""")

    # Generate impl of `inner_full_name`.
    f.write("""
    #[inline]
    pub(crate) fn inner_full_name(self) -> &'static str {
        match self {
            Script::Unknown => "Unknown",
            Script::Common => "Common",
            Script::Inherited => "Inherited",
""")
    for script in script_list:
        f.write("            Script::%s => \"%s\",\n" % (longforms[script], longforms[script]))
    f.write("""        }
    }
""")

    # Generate impl of `inner_from_full_name`.
    f.write("""
    #[inline]
    pub(crate) fn inner_from_full_name(input: &str) -> Option<Self> {
        match input {
            "Unknown" => Some(Script::Unknown),
            "Common" => Some(Script::Common),
            "Inherited" => Some(Script::Inherited),
""")
    for script in script_list:
        f.write("            \"%s\" => Some(Script::%s),\n" % (longforms[script], longforms[script]))
    f.write("            _ => None,\n" )
    f.write("""        }
    }
""")

    # Generate impl of `inner_short_name`
    f.write("""
    #[inline]
    pub(crate) fn inner_short_name(self) -> &'static str {
        match self {
            Script::Unknown => "",
            Script::Common => "Zyyy",
            Script::Inherited => "Zinh",
""")
    for script in script_list:
        f.write("            Script::%s => \"%s\",\n" % (longforms[script], script))
    f.write("""        }
    }
""")

    # Generate impl of `inner_from_short_name`
    f.write("""
    #[inline]
    pub(crate) fn inner_from_short_name(input: &str) -> Option<Self> {
        match input {
            "Zyyy" => Some(Script::Common),
            "Zinh" => Some(Script::Inherited),
""")
    for script in script_list:
        f.write("            \"%s\" => Some(Script::%s),\n" % (script, longforms[script]))
    f.write("""        _ => None,\n""")
    f.write("""        }
    }
""")

    # Generate impl of `for_integer`
    f.write("""
    #[inline]
    pub(crate) fn for_integer(value: u8) -> Self {
        match value {
""")
    for (i, script) in enumerate(script_list):
        f.write("            %s => Script::%s,\n" % (i, longforms[script]))
    f.write("""            _ => unreachable!(),
        }
    }
""")

    # Close `impl Script` section
    f.write("""
}
""")

def extension_name(ext):
    """Get the rust source for a given ScriptExtension"""
    return "script_extensions::%s" % "_".join([e.upper() for e in ext])


if __name__ == "__main__":
    r = "tables.rs"
    if os.path.exists(r):
        os.remove(r)
    with open(r, "w") as rf:
        # write the file's preamble
        rf.write(preamble)
        rf.write("""
/// The version of [Unicode](http://www.unicode.org/)
/// that this version of unicode-script is based on.
pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);
""" % UNICODE_VERSION)


        (longforms, shortforms) = aliases()

        scripts = load_properties("Scripts.txt", [])

        script_table = []
        script_list = []

        for script in scripts:
            if script not in ["Common", "Unknown", "Inherited"]:
                script_list.append(shortforms[script])
            script_table.extend([(x, y, shortforms[script]) for (x, y) in scripts[script]])
        script_list.sort()
        script_table.sort(key=lambda w: w[0])


        extensions = load_properties("ScriptExtensions.txt", [])
        extension_table = []
        extension_list = []

        for ext in extensions:
            split = ext.split(" ")
            split.sort()
            output_ext = [ext]
            if len(split) > 1:
                extension_list.append(split)
                output_ext = split
            extension_table.extend([(x, y, output_ext) for (x, y) in extensions[ext]])
        extension_table.sort(key=lambda w: w[0])


        emit_enums(rf, script_list, extension_list, longforms)
        emit_search(rf)

        emit_table(rf, "SCRIPTS", script_table, t_type = "&'static [(char, char, Script)]",
                   is_pub=False , pfun=lambda x: "(%s,%s, Script::%s)" % (escape_char(x[0]), escape_char(x[1]), longforms[x[2]]))
        emit_table(rf, "SCRIPT_EXTENSIONS", extension_table, t_type = "&'static [(char, char, ScriptExtension)]",
                   is_pub=False , pfun=lambda x: "(%s,%s,%s)" % (escape_char(x[0]), escape_char(x[1]), extension_name(x[2])))

        # emit_table(rf, "FOObar", properties)

        rf.write(ending)