File: word_boundary_ascii.rs

package info (click to toggle)
chromium 120.0.6099.224-1~deb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 6,112,112 kB
  • sloc: cpp: 32,907,025; ansic: 8,148,123; javascript: 3,679,536; python: 2,031,248; asm: 959,718; java: 804,675; xml: 617,256; sh: 111,417; objc: 100,835; perl: 88,443; cs: 53,032; makefile: 29,579; fortran: 24,137; php: 21,162; tcl: 21,147; sql: 20,809; ruby: 17,735; pascal: 12,864; yacc: 8,045; lisp: 3,388; lex: 1,323; ada: 727; awk: 329; jsp: 267; csh: 117; exp: 43; sed: 37
file content (9 lines) | stat: -rw-r--r-- 477 bytes parent folder | download | duplicates (65) 
1
2
3
4
5
6
7
8
9
 
// ASCII word boundaries are completely oblivious to Unicode characters.
// For Unicode word boundaries, the tests are precisely inverted.
matiter!(ascii1, r"(?-u:\b)x(?-u:\b)", "áxβ", (2, 3));
matiter!(ascii2, r"(?-u:\B)x(?-u:\B)", "áxβ");
matiter!(ascii3, r"(?-u:\B)", "0\u{7EF5E}", (2, 2), (3, 3), (4, 4), (5, 5));

// We still get Unicode word boundaries by default in byte regexes.
matiter!(unicode1, r"\bx\b", "áxβ");
matiter!(unicode2, r"\Bx\B", "áxβ", (2, 3));