DXR will be turned off on Tuesday, December 29th. It will redirect to Searchfox.
See the announcement on Discourse.

DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (c68fe15a81fc)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465
#!/usr/bin/env python
#
# Copyright 2011-2015 The Rust Project Developers. See the COPYRIGHT
# 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
# 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:
# This script uses the following Unicode tables:
# - DerivedNormalizationProps.txt
# - ReadMe.txt
# - UnicodeData.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, collections

preamble = '''// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
// 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
// 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
// NOTE: The following code was generated by "scripts/unicode.py", do not edit directly

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

# Mapping taken from Table 12 from:
# Mapping taken from Table 12 from:
# http://www.unicode.org/reports/tr44/#General_Category_Values
expanded_categories = {
    'Lu': ['LC', 'L'], 'Ll': ['LC', 'L'], 'Lt': ['LC', 'L'],
    'Lm': ['L'], 'Lo': ['L'],
    'Mn': ['M'], 'Mc': ['M'], 'Me': ['M'],
    'Mn': ['M'], 'Mc': ['M'], 'Me': ['M'],
    'Nd': ['N'], 'Nl': ['N'], 'No': ['No'],
    'Pc': ['P'], 'Pd': ['P'], 'Ps': ['P'], 'Pe': ['P'],
    'Pi': ['P'], 'Pf': ['P'], 'Po': ['P'],
    'Sm': ['S'], 'Sc': ['S'], 'Sk': ['S'], 'So': ['S'],
    'Zs': ['Z'], 'Zl': ['Z'], 'Zp': ['Z'],
    'Zs': ['Z'], 'Zl': ['Z'], 'Zp': ['Z'],
    'Cc': ['C'], 'Cf': ['C'], 'Cs': ['C'], 'Co': ['C'], 'Cn': ['C'],
}

# these are the surrogate codepoints, which are not valid rust characters
surrogate_codepoints = (0xd800, 0xdfff)
surrogate_codepoints = (0xd800, 0xdfff)


def fetch(f):
    if not os.path.exists(os.path.basename(f)):
        os.system("curl -O http://www.unicode.org/Public/UNIDATA/%s"
                  % f)

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

def is_surrogate(n):
    return surrogate_codepoints[0] <= n <= surrogate_codepoints[1]


def load_unicode_data(f):
    fetch(f)
    combines = {}
    canon_decomp = {}
    compat_decomp = {}
    compat_decomp = {}
    general_category_mark = []

    udict = {};
    range_start = -1;
    range_start = -1;
    for line in fileinput.input(f):
        data = line.split(';');
        if len(data) != 15:
            continue
        cp = int(data[0], 16);
        cp = int(data[0], 16);
        if is_surrogate(cp):
            continue
        if range_start >= 0:
            for i in xrange(range_start, cp):
                udict[i] = data;
                udict[i] = data;
            range_start = -1;
        if data[1].endswith(", First>"):
            range_start = cp;
            continue;
        udict[cp] = data;
        udict[cp] = data;

    for code in udict:
        [code_org, name, gencat, combine, bidi,
         decomp, deci, digit, num, mirror,
         decomp, deci, digit, num, mirror,
         old, iso, upcase, lowcase, titlecase ] = udict[code];

        # store decomposition, if given
        if decomp != "":
            if decomp.startswith('<'):
            if decomp.startswith('<'):
                seq = []
                for i in decomp.split()[1:]:
                    seq.append(int(i, 16))
                compat_decomp[code] = seq
            else:
            else:
                seq = []
                for i in decomp.split():
                    seq.append(int(i, 16))
                canon_decomp[code] = seq


        # record combining class, if any
        if combine != "0":
            if combine not in combines:
                combines[combine] = []
            combines[combine].append(code)

        if 'M' in [gencat] + expanded_categories.get(gencat, []):
            general_category_mark.append(code)
            general_category_mark.append(code)
    general_category_mark = group_cat(general_category_mark)

    combines = to_combines(group_cats(combines))

    return (canon_decomp, compat_decomp, combines, general_category_mark)
    return (canon_decomp, compat_decomp, combines, general_category_mark)

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

def group_cat(cat):
def group_cat(cat):
    cat_out = []
    letters = sorted(set(cat))
    cur_start = letters.pop(0)
    cur_end = cur_start
    cur_end = cur_start
    for letter in letters:
        assert letter > cur_end, \
            "cur_end: %s, letter: %s" % (hex(cur_end), hex(letter))
        if letter == cur_end + 1:
            cur_end = letter
            cur_end = letter
        else:
            cat_out.append((cur_start, cur_end))
            cur_start = cur_end = letter
    cat_out.append((cur_start, cur_end))
    return cat_out
    return cat_out

def ungroup_cat(cat):
    cat_out = []
    cat_out = []
    for (lo, hi) in cat:
        while lo <= hi:
            cat_out.append(lo)
            lo += 1
    return cat_out

def to_combines(combs):
def to_combines(combs):
    combs_out = []
    for comb in combs:
        for (lo, hi) in combs[comb]:
            combs_out.append((lo, hi, comb))
    combs_out.sort(key=lambda comb: comb[0])
    combs_out.sort(key=lambda comb: comb[0])
    return combs_out

def format_table_content(f, content, indent):
    indent = " "*indent
    for c in content:
    for c in content:
        f.write("%s%s,\n" % (indent, c))

def load_properties(f, interestingprops):
def load_properties(f, interestingprops):
    fetch(f)
    props = {}
    re1 = re.compile("^ *([0-9A-F]+) *; *(\w+)")
    re2 = re.compile("^ *([0-9A-F]+)\.\.([0-9A-F]+) *; *(\w+)")


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


    # optimize if possible
    for prop in props:
        props[prop] = group_cat(ungroup_cat(props[prop]))

    return props

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

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]))):
    pub_string = ""
    if is_pub:
        pub_string = "pub "
        pub_string = "pub "
    f.write("    %sconst %s: %s = &[\n" % (pub_string, name, t_type))
    format_table_content(f, [pfun(d) for d in t_data], 8)
    f.write("\n    ];\n\n")

def emit_strtab_table(f, name, keys, vfun, is_pub=True,
                      tab_entry_type='char', slice_element_sfun=escape_char):
    pub_string = ""
    pub_string = ""
    if is_pub:
        pub_string = "pub "
    f.write("    %s const %s: &'static [(char, Slice)] = &[\n"
            % (pub_string, name))

    strtab = collections.OrderedDict()
    strtab_offset = 0
    strtab_offset = 0

    # TODO: a more sophisticated algorithm here would not only check for the
    # existence of v in the strtab, but also v in contiguous substrings of
    # strtab, if that's possible.
    for k in keys:
    for k in keys:
        v = tuple(vfun(k))
        if v in strtab:
            item_slice = strtab[v]
        else:
        else:
            value_len = len(v)
            item_slice = (strtab_offset, value_len)
            strtab[v] = item_slice
            strtab_offset += value_len


        f.write("%s(%s, Slice { offset: %d, length: %d }),\n"
                % (" "*8, escape_char(k), item_slice[0], item_slice[1]))

    f.write("\n    ];\n\n")


    f.write("    %s const %s_STRTAB: &'static [%s] = &[\n"
            % (pub_string, name, tab_entry_type))

    for (v, _) in strtab.iteritems():
        f.write("%s%s,\n" % (" "*8, ', '.join(slice_element_sfun(c) for c in v)))

    f.write("\n    ];\n\n")
    f.write("\n    ];\n\n")

def emit_norm_module(f, canon, compat, combine, norm_props, general_category_mark):
    canon_keys = canon.keys()
    canon_keys.sort()
    canon_keys.sort()

    compat_keys = compat.keys()
    compat_keys.sort()

    canon_comp = {}
    canon_comp = {}
    comp_exclusions = norm_props["Full_Composition_Exclusion"]
    for char in canon_keys:
        if True in map(lambda (lo, hi): lo <= char <= hi, comp_exclusions):
            continue
        decomp = canon[char]
        decomp = canon[char]
        if len(decomp) == 2:
            if not canon_comp.has_key(decomp[0]):
                canon_comp[decomp[0]] = []
            canon_comp[decomp[0]].append( (decomp[1], char) )
            canon_comp[decomp[0]].append( (decomp[1], char) )
    canon_comp_keys = canon_comp.keys()
    canon_comp_keys.sort()

    f.write("pub mod normalization {\n")
    f.write("""
    f.write("""
pub struct Slice {
  pub offset: u16,
  pub length: u16,
}
""")
""")

    def mkdata_fun(table):
        def f(char):
            return table[char]
        return f
        return f

    # TODO: should the strtab of these two tables be of type &'static str, for
    # smaller data?
    f.write("    // Canonical decompositions\n")
    f.write("    // Canonical decompositions\n")
    emit_strtab_table(f, "canonical_table", canon_keys,
                      vfun=mkdata_fun(canon))

    f.write("    // Compatibility decompositions\n")
    emit_strtab_table(f, "compatibility_table", compat_keys,
    emit_strtab_table(f, "compatibility_table", compat_keys,
                      vfun=mkdata_fun(compat))

    def comp_vfun(char):
        return sorted(canon_comp[char], lambda x, y: x[0] - y[0])


    f.write("    // Canonical compositions\n")
    # "&'static [(char, &'static [(char, char)])]", pfun=comp_pfun)
    emit_strtab_table(f, "composition_table", canon_comp_keys,
                      vfun=comp_vfun,
                      vfun=comp_vfun,
                      tab_entry_type="(char, char)",
                      slice_element_sfun=lambda pair: "(%s,%s)" % (escape_char(pair[0]),
                                                                   escape_char(pair[1])))

    f.write("""
    f.write("""
    fn bsearch_range_value_table(c: char, r: &'static [(char, char, u8)]) -> u8 {
        use std::cmp::Ordering::{Equal, Less, Greater};
        match r.binary_search_by(|&(lo, hi, _)| {
            if lo <= c && c <= hi { Equal }
            else if hi < c { Less }
            else if hi < c { Less }
            else { Greater }
        }) {
            Ok(idx) => {
                let (_, _, result) = r[idx];
                result
                result
            }
            }
            Err(_) => 0
        }
    }\n
""")


    emit_table(f, "combining_class_table", combine, "&'static [(char, char, u8)]", is_pub=False,
            pfun=lambda x: "(%s,%s,%s)" % (escape_char(x[0]), escape_char(x[1]), x[2]))

    f.write("    pub fn canonical_combining_class(c: char) -> u8 {\n"
        + "        bsearch_range_value_table(c, combining_class_table)\n"
        + "        bsearch_range_value_table(c, combining_class_table)\n"
        + "    }\n")

    f.write("""
    fn bsearch_range_table(c: char, r: &'static [(char, char)]) -> bool {
        use std::cmp::Ordering::{Equal, Less, Greater};
        use std::cmp::Ordering::{Equal, Less, Greater};
        r.binary_search_by(|&(lo, hi)| {
             if lo <= c && c <= hi {
                 Equal
             } else if hi < c {
             } else if hi < c {
                 Less
             } else {
                 Greater
             }
         })
         })
         .is_ok()
    }

    /// Return whether the given character is a combining mark (`General_Category=Mark`)
    /// Return whether the given character is a combining mark (`General_Category=Mark`)
    pub fn is_combining_mark(c: char) -> bool {
        bsearch_range_table(c, general_category_mark)
    }

""")
""")

    emit_table(f, "general_category_mark", general_category_mark, "&'static [(char, char)]", is_pub=False,
            pfun=lambda x: "(%s,%s)" % (escape_char(x[0]), escape_char(x[1])))

    f.write("""
    f.write("""
}

""")


if __name__ == "__main__":
    r = "tables.rs"
    if os.path.exists(r):
        os.remove(r)
    with open(r, "w") as rf:
    with open(r, "w") as rf:
        # write the file's preamble
        rf.write(preamble)

        # download and parse all the data
        fetch("ReadMe.txt")
        with open("ReadMe.txt") as readme:
            pattern = "for Version (\d+)\.(\d+)\.(\d+) of the Unicode"
            pattern = "for Version (\d+)\.(\d+)\.(\d+) of the Unicode"
            unicode_version = re.search(pattern, readme.read()).groups()
        rf.write("""
/// The version of [Unicode](http://www.unicode.org/)
/// that this version of unicode-normalization is based on.
pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);
pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);

""" % unicode_version)
        (canon_decomp, compat_decomp, combines, general_category_mark) = \
            load_unicode_data("UnicodeData.txt")
        norm_props = load_properties("DerivedNormalizationProps.txt",
        norm_props = load_properties("DerivedNormalizationProps.txt",
                     ["Full_Composition_Exclusion"])

        # normalizations and conversions module
        emit_norm_module(rf, canon_decomp, compat_decomp, combines, norm_props,
                         general_category_mark)