rustc/vendor/unicode-security/scripts/unicode.py
2020-04-04 01:11:41 +01:00

227 lines
6.9 KiB
Python

#!/usr/bin/env python3
#
# 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 security tables:
# - IdentifierStatus.txt
# - ReadMe.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, operator
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.
//
// 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)]
'''
UNICODE_VERSION = (12, 1, 0)
UNICODE_VERSION_NUMBER = "%s.%s.%s" %UNICODE_VERSION
def fetch(f):
if not os.path.exists(os.path.basename(f)):
os.system("curl -O http://www.unicode.org/Public/security/%s/%s"
% (UNICODE_VERSION_NUMBER, f))
if not os.path.exists(os.path.basename(f)):
sys.stderr.write("cannot load %s\n" % f)
exit(1)
# Implementation from unicode-segmentation
def load_properties(f, interestingprops = None):
fetch(f)
props = {}
re1 = re.compile(r"^ *([0-9A-F]+) *; *(\w+)")
re2 = re.compile(r"^ *([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)
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
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)
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])), 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_identifier_module(f):
f.write("pub mod identifier {")
f.write("""
#[derive(Copy, Clone, Hash, Eq, PartialEq, Ord, PartialOrd, Debug)]
#[allow(non_camel_case_types)]
/// https://www.unicode.org/reports/tr39/#Identifier_Status_and_Type
pub enum IdentifierType {
// Restricted
Not_Character,
Deprecated,
Default_Ignorable,
Not_NFKC,
Not_XID,
Exclusion,
Obsolete,
Technical,
Uncommon_Use,
Limited_Use,
// Allowed
Inclusion,
Recommended
}
#[inline]
pub fn identifier_status_allowed(c: char) -> bool {
// FIXME: do we want to special case ASCII here?
match c as usize {
_ => super::util::bsearch_range_table(c, IDENTIFIER_STATUS)
}
}
#[inline]
pub fn identifier_type(c: char) -> Option<IdentifierType> {
// FIXME: do we want to special case ASCII here?
match c as usize {
_ => super::util::bsearch_range_value_table(c, IDENTIFIER_TYPE)
}
}
""")
f.write(" // Identifier status table:\n")
identifier_status_table = load_properties("IdentifierStatus.txt")
emit_table(f, "IDENTIFIER_STATUS", identifier_status_table['Allowed'], "&'static [(char, char)]", is_pub=False,
pfun=lambda x: "(%s,%s)" % (escape_char(x[0]), escape_char(x[1])))
identifier_type = load_properties("IdentifierType.txt")
type_table = []
for ty in identifier_type:
type_table.extend([(x, y, ty) for (x, y) in identifier_type[ty]])
type_table.sort(key=lambda w: w[0])
emit_table(f, "IDENTIFIER_TYPE", type_table, "&'static [(char, char, IdentifierType)]", is_pub=False,
pfun=lambda x: "(%s,%s, IdentifierType::%s)" % (escape_char(x[0]), escape_char(x[1]), x[2]))
f.write("}\n\n")
def emit_util_mod(f):
f.write("""
pub mod util {
use core::result::Result::{Ok, Err};
#[inline]
pub fn bsearch_range_table(c: char, r: &'static [(char,char)]) -> bool {
use core::cmp::Ordering::{Equal, Less, Greater};
r.binary_search_by(|&(lo,hi)| {
if lo <= c && c <= hi { Equal }
else if hi < c { Less }
else { Greater }
}).is_ok()
}
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
}
}
}
""")
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-security is based on.
pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);
""" % UNICODE_VERSION)
emit_util_mod(rf)
### identifier module
emit_identifier_module(rf)