]>
git.proxmox.com Git - rustc.git/blob - src/etc/unicode.py
3 # Copyright 2011-2013 The Rust Project Developers. See the COPYRIGHT
4 # file at the top-level directory of this distribution and at
5 # http://rust-lang.org/COPYRIGHT.
7 # Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
8 # http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
9 # <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
10 # option. This file may not be copied, modified, or distributed
11 # except according to those terms.
13 # This script uses the following Unicode tables:
14 # - DerivedCoreProperties.txt
15 # - DerivedNormalizationProps.txt
16 # - EastAsianWidth.txt
17 # - auxiliary/GraphemeBreakProperty.txt
23 # Since this should not require frequent updates, we just store this
24 # out-of-line and check the unicode.rs file into git.
26 import fileinput
, re
, os
, sys
, operator
28 preamble
= '''// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT
29 // file at the top-level directory of this distribution and at
30 // http://rust-lang.org/COPYRIGHT.
32 // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
33 // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
34 // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
35 // option. This file may not be copied, modified, or distributed
36 // except according to those terms.
38 // NOTE: The following code was generated by "src/etc/unicode.py", do not edit directly
40 #![allow(missing_docs, non_upper_case_globals, non_snake_case)]
43 # Mapping taken from Table 12 from:
44 # http://www.unicode.org/reports/tr44/#General_Category_Values
45 expanded_categories
= {
46 'Lu': ['LC', 'L'], 'Ll': ['LC', 'L'], 'Lt': ['LC', 'L'],
47 'Lm': ['L'], 'Lo': ['L'],
48 'Mn': ['M'], 'Mc': ['M'], 'Me': ['M'],
49 'Nd': ['N'], 'Nl': ['N'], 'No': ['No'],
50 'Pc': ['P'], 'Pd': ['P'], 'Ps': ['P'], 'Pe': ['P'],
51 'Pi': ['P'], 'Pf': ['P'], 'Po': ['P'],
52 'Sm': ['S'], 'Sc': ['S'], 'Sk': ['S'], 'So': ['S'],
53 'Zs': ['Z'], 'Zl': ['Z'], 'Zp': ['Z'],
54 'Cc': ['C'], 'Cf': ['C'], 'Cs': ['C'], 'Co': ['C'], 'Cn': ['C'],
57 # these are the surrogate codepoints, which are not valid rust characters
58 surrogate_codepoints
= (0xd800, 0xdfff)
61 if not os
.path
.exists(os
.path
.basename(f
)):
62 os
.system("curl -O http://www.unicode.org/Public/UNIDATA/%s"
65 if not os
.path
.exists(os
.path
.basename(f
)):
66 sys
.stderr
.write("cannot load %s" % f
)
70 return surrogate_codepoints
[0] <= n
<= surrogate_codepoints
[1]
72 def load_unicode_data(f
):
84 for line
in fileinput
.input(f
):
85 data
= line
.split(';');
88 cp
= int(data
[0], 16);
92 for i
in xrange(range_start
, cp
):
95 if data
[1].endswith(", First>"):
101 [code_org
, name
, gencat
, combine
, bidi
,
102 decomp
, deci
, digit
, num
, mirror
,
103 old
, iso
, upcase
, lowcase
, titlecase
] = udict
[code
];
105 # generate char to char direct common and simple conversions
106 # uppercase to lowercase
107 if lowcase
!= "" and code_org
!= lowcase
:
108 to_lower
[code
] = (int(lowcase
, 16), 0, 0)
110 # lowercase to uppercase
111 if upcase
!= "" and code_org
!= upcase
:
112 to_upper
[code
] = (int(upcase
, 16), 0, 0)
115 if titlecase
.strip() != "" and code_org
!= titlecase
:
116 to_title
[code
] = (int(titlecase
, 16), 0, 0)
118 # store decomposition, if given
120 if decomp
.startswith('<'):
122 for i
in decomp
.split()[1:]:
123 seq
.append(int(i
, 16))
124 compat_decomp
[code
] = seq
127 for i
in decomp
.split():
128 seq
.append(int(i
, 16))
129 canon_decomp
[code
] = seq
131 # place letter in categories as appropriate
132 for cat
in [gencat
, "Assigned"] + expanded_categories
.get(gencat
, []):
133 if cat
not in gencats
:
135 gencats
[cat
].append(code
)
137 # record combining class, if any
139 if combine
not in combines
:
140 combines
[combine
] = []
141 combines
[combine
].append(code
)
143 # generate Not_Assigned from Assigned
144 gencats
["Cn"] = gen_unassigned(gencats
["Assigned"])
145 # Assigned is not a real category
146 del(gencats
["Assigned"])
147 # Other contains Not_Assigned
148 gencats
["C"].extend(gencats
["Cn"])
149 gencats
= group_cats(gencats
)
150 combines
= to_combines(group_cats(combines
))
152 return (canon_decomp
, compat_decomp
, gencats
, combines
, to_upper
, to_lower
, to_title
)
154 def load_special_casing(f
, to_upper
, to_lower
, to_title
):
156 for line
in fileinput
.input(f
):
157 data
= line
.split('#')[0].split(';')
159 code
, lower
, title
, upper
, _comment
= data
161 code
, lower
, title
, upper
, condition
, _comment
= data
162 if condition
.strip(): # Only keep unconditional mappins
167 lower
= lower
.strip()
168 title
= title
.strip()
169 upper
= upper
.strip()
171 for (map_
, values
) in [(to_lower
, lower
), (to_upper
, upper
), (to_title
, title
)]:
173 values
= [int(i
, 16) for i
in values
.split()]
174 for _
in range(len(values
), 3):
176 assert len(values
) == 3
179 def group_cats(cats
):
182 cats_out
[cat
] = group_cat(cats
[cat
])
187 letters
= sorted(set(cat
))
188 cur_start
= letters
.pop(0)
190 for letter
in letters
:
191 assert letter
> cur_end
, \
192 "cur_end: %s, letter: %s" % (hex(cur_end
), hex(letter
))
193 if letter
== cur_end
+ 1:
196 cat_out
.append((cur_start
, cur_end
))
197 cur_start
= cur_end
= letter
198 cat_out
.append((cur_start
, cur_end
))
201 def ungroup_cat(cat
):
209 def gen_unassigned(assigned
):
210 assigned
= set(assigned
)
211 return ([i
for i
in range(0, 0xd800) if i
not in assigned
] +
212 [i
for i
in range(0xe000, 0x110000) if i
not in assigned
])
214 def to_combines(combs
):
217 for (lo
, hi
) in combs
[comb
]:
218 combs_out
.append((lo
, hi
, comb
))
219 combs_out
.sort(key
=lambda comb
: comb
[0])
222 def format_table_content(f
, content
, indent
):
225 for chunk
in content
.split(","):
226 if len(line
) + len(chunk
) < 98:
233 f
.write(line
+ ",\n")
234 line
= " "*indent
+ chunk
237 def load_properties(f
, interestingprops
):
240 re1
= re
.compile("^ *([0-9A-F]+) *; *(\w+)")
241 re2
= re
.compile("^ *([0-9A-F]+)\.\.([0-9A-F]+) *; *(\w+)")
243 for line
in fileinput
.input(os
.path
.basename(f
)):
260 if interestingprops
and prop
not in interestingprops
:
264 if prop
not in props
:
266 props
[prop
].append((d_lo
, d_hi
))
268 # optimize if possible
270 props
[prop
] = group_cat(ungroup_cat(props
[prop
]))
275 return "'\\u{%x}'" % c
if c
!= 0 else "'\\0'"
277 def emit_bsearch_range_table(f
):
279 fn bsearch_range_table(c: char, r: &'static [(char, char)]) -> bool {
280 use core::cmp::Ordering::{Equal, Less, Greater};
281 r.binary_search_by(|&(lo, hi)| {
294 def emit_table(f
, name
, t_data
, t_type
= "&'static [(char, char)]", is_pub
=True,
295 pfun
=lambda x
: "(%s,%s)" % (escape_char(x
[0]), escape_char(x
[1]))):
299 f
.write(" %sconst %s: %s = &[\n" % (pub_string
, name
, t_type
))
307 format_table_content(f
, data
, 8)
310 def emit_property_module(f
, mod
, tbl
, emit
):
311 f
.write("pub mod %s {\n" % mod
)
312 for cat
in sorted(emit
):
313 emit_table(f
, "%s_table" % cat
, tbl
[cat
])
314 f
.write(" pub fn %s(c: char) -> bool {\n" % cat
)
315 f
.write(" super::bsearch_range_table(c, %s_table)\n" % cat
)
319 def emit_conversions_module(f
, to_upper
, to_lower
, to_title
):
320 f
.write("pub mod conversions {")
322 use core::option::Option;
323 use core::option::Option::{Some, None};
325 pub fn to_lower(c: char) -> [char; 3] {
326 match bsearch_case_table(c, to_lowercase_table) {
327 None => [c, '\\0', '\\0'],
328 Some(index) => to_lowercase_table[index].1,
332 pub fn to_upper(c: char) -> [char; 3] {
333 match bsearch_case_table(c, to_uppercase_table) {
334 None => [c, '\\0', '\\0'],
335 Some(index) => to_uppercase_table[index].1,
339 fn bsearch_case_table(c: char, table: &'static [(char, [char; 3])]) -> Option<usize> {
340 table.binary_search_by(|&(key, _)| key.cmp(&c)).ok()
344 t_type
= "&'static [(char, [char; 3])]"
345 pfun
= lambda x
: "(%s,[%s,%s,%s])" % (
346 escape_char(x
[0]), escape_char(x
[1][0]), escape_char(x
[1][1]), escape_char(x
[1][2]))
347 emit_table(f
, "to_lowercase_table",
348 sorted(to_lower
.iteritems(), key
=operator
.itemgetter(0)),
349 is_pub
=False, t_type
= t_type
, pfun
=pfun
)
350 emit_table(f
, "to_uppercase_table",
351 sorted(to_upper
.iteritems(), key
=operator
.itemgetter(0)),
352 is_pub
=False, t_type
= t_type
, pfun
=pfun
)
355 def emit_norm_module(f
, canon
, compat
, combine
, norm_props
):
356 canon_keys
= canon
.keys()
359 compat_keys
= compat
.keys()
363 comp_exclusions
= norm_props
["Full_Composition_Exclusion"]
364 for char
in canon_keys
:
365 if True in map(lambda (lo
, hi
): lo
<= char
<= hi
, comp_exclusions
):
369 if not canon_comp
.has_key(decomp
[0]):
370 canon_comp
[decomp
[0]] = []
371 canon_comp
[decomp
[0]].append( (decomp
[1], char
) )
372 canon_comp_keys
= canon_comp
.keys()
373 canon_comp_keys
.sort()
375 if __name__
== "__main__":
377 if os
.path
.exists(r
):
379 with
open(r
, "w") as rf
:
380 # write the file's preamble
383 # download and parse all the data
385 with
open("ReadMe.txt") as readme
:
386 pattern
= "for Version (\d+)\.(\d+)\.(\d+) of the Unicode"
387 unicode_version
= re
.search(pattern
, readme
.read()).groups()
389 /// The version of [Unicode](http://www.unicode.org/)
390 /// that the unicode parts of `CharExt` and `UnicodeStrPrelude` traits are based on.
391 pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);
392 """ % unicode_version
)
393 (canon_decomp
, compat_decomp
, gencats
, combines
,
394 to_upper
, to_lower
, to_title
) = load_unicode_data("UnicodeData.txt")
395 load_special_casing("SpecialCasing.txt", to_upper
, to_lower
, to_title
)
396 want_derived
= ["XID_Start", "XID_Continue", "Alphabetic", "Lowercase", "Uppercase",
397 "Cased", "Case_Ignorable"]
398 derived
= load_properties("DerivedCoreProperties.txt", want_derived
)
399 scripts
= load_properties("Scripts.txt", [])
400 props
= load_properties("PropList.txt",
401 ["White_Space", "Join_Control", "Noncharacter_Code_Point", "Pattern_White_Space"])
402 norm_props
= load_properties("DerivedNormalizationProps.txt",
403 ["Full_Composition_Exclusion"])
405 # bsearch_range_table is used in all the property modules below
406 emit_bsearch_range_table(rf
)
409 for (name
, cat
, pfuns
) in ("general_category", gencats
, ["N", "Cc"]), \
410 ("derived_property", derived
, want_derived
), \
411 ("property", props
, ["White_Space", "Pattern_White_Space"]):
412 emit_property_module(rf
, name
, cat
, pfuns
)
414 # normalizations and conversions module
415 emit_norm_module(rf
, canon_decomp
, compat_decomp
, combines
, norm_props
)
416 emit_conversions_module(rf
, to_upper
, to_lower
, to_title
)