Module: RE2

Defined in:
ext/re2/re2.cc,
lib/re2/regexp.rb,
lib/re2/string.rb,
lib/re2/scanner.rb,
lib/re2/version.rb,
lib/re2/match_data.rb

Defined Under Namespace

Modules: String Classes: MatchData, Regexp, Scanner, Set

Constant Summary collapse

VERSION = 
"2.29.0"

Class Method Summary collapse

Class Method Details

.escape(unquoted) ⇒ String

Returns a version of str with all potentially meaningful regexp characters escaped using `QuoteMeta`. The returned string, used as a regular expression, will exactly match the original string.

Examples:

RE2.escape("1.5-2.0?")         #=> "1\\.5\\-2\\.0\\?"
RE2.quote("1.5-2.0?")          #=> "1\\.5\\-2\\.0\\?"
RE2::Regexp.escape("1.5-2.0?") #=> "1\\.5\\-2\\.0\\?"
RE2::Regexp.quote("1.5-2.0?")  #=> "1\\.5\\-2\\.0\\?"

Parameters:

  • unquoted (String) —

    the unquoted string

Returns:

  • (String) —

    the escaped string

Raises:

  • (TypeError) —

    if the given unquoted string cannot be coerced to a String



2457
2458
2459
2460
2461
2462
2463
2464
 
# File 'ext/re2/re2.cc', line 2457

static VALUE re2_escape(VALUE, VALUE unquoted) {
  StringValue(unquoted);

  std::string quoted_string = RE2::QuoteMeta(
      re2::StringPiece(RSTRING_PTR(unquoted), RSTRING_LEN(unquoted)));

  return rb_str_new(quoted_string.data(), quoted_string.size());
}

.extract(text, pattern, rewrite) ⇒ String?

If pattern matches text, returns a copy of rewrite with substitutions using `Extract`. Non-matching portions of text are ignored.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

RE2.extract("alice@example.com", '(\w+)@(\w+)', '\2-\1')
#=> "example-alice"
RE2.extract("no match", '(\d+)', '\1') #=> nil

Parameters:

  • text (String) —

    the string from which to extract

  • pattern (String, RE2::Regexp) —

    a regexp matching the text

  • rewrite (String) —

    the rewrite string with \1-style substitutions

Returns:

  • (String, nil) —

    the extracted string on a successful match or nil if there is no match

Raises:

  • (TypeError) —

    if the given rewrite or pattern (if not provided as a Regexp) cannot be coerced to Strings



2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
 
# File 'ext/re2/re2.cc', line 2387

static VALUE re2_extract(VALUE, VALUE text, VALUE pattern,
    VALUE rewrite) {
  re2_pattern *p = nullptr;

  /* Coerce and freeze all arguments before any C++ allocations so that any
   * Ruby exceptions (via longjmp) cannot bypass C++ destructors and leak
   * memory, and later coercions cannot mutate earlier strings.
   */
  StringValue(text);
  text = rb_str_new_frozen(text);
  if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
    p = unwrap_re2_regexp(pattern);
  } else {
    StringValue(pattern);
    pattern = rb_str_new_frozen(pattern);
  }
  StringValue(rewrite);
  rewrite = rb_str_new_frozen(rewrite);

  std::string out;

  nogvl_extract_arg arg;
  arg.text = re2::StringPiece(RSTRING_PTR(text), RSTRING_LEN(text));
  if (p) {
    arg.pattern = p->pattern;
  } else {
    arg.pattern = nullptr;
    arg.string_pattern = re2::StringPiece(
        RSTRING_PTR(pattern), RSTRING_LEN(pattern));
  }
  arg.rewrite = re2::StringPiece(
      RSTRING_PTR(rewrite), RSTRING_LEN(rewrite));
  arg.out = &out;
  arg.extracted = false;

#ifdef _WIN32
  nogvl_extract(&arg);
#else
  rb_thread_call_without_gvl(nogvl_extract, &arg, NULL, NULL);
#endif

  RB_GC_GUARD(text);
  RB_GC_GUARD(rewrite);
  RB_GC_GUARD(pattern);

  if (arg.extracted) {
    return encoded_str_new(out.data(), out.size(),
        p ? p->pattern->options().encoding()
          : RE2::Options::EncodingUTF8);
  } else {
    return Qnil;
  }
}

.global_replace(str, pattern, rewrite) ⇒ String

Return a copy of str with pattern replaced by rewrite using `GlobalReplace`.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

re2 = RE2::Regexp.new("oo?")
RE2.global_replace("whoops-doops", re2, "e") #=> "wheps-deps"
RE2.global_replace("hello there", "e", "i")  #=> "hillo thiri"

Parameters:

  • str (String) —

    the string to modify

  • pattern (String, RE2::Regexp) —

    a regexp matching text to be replaced

  • rewrite (String) —

    the string to replace with

Returns:

  • (String) —

    the resulting string

Raises:

  • (TypeError) —

    if the given rewrite or pattern (if not provided as a Regexp) cannot be coerced to Strings



2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
 
# File 'ext/re2/re2.cc', line 2311

static VALUE re2_global_replace(VALUE, VALUE str, VALUE pattern,
                               VALUE rewrite) {
  re2_pattern *p = nullptr;

  /* Coerce and freeze all arguments before any C++ allocations so that any
   * Ruby exceptions (via longjmp) cannot bypass C++ destructors and leak
   * memory, and later coercions cannot mutate earlier strings.
   */
  StringValue(str);
  str = rb_str_new_frozen(str);
  if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
    p = unwrap_re2_regexp(pattern);
  } else {
    StringValue(pattern);
    pattern = rb_str_new_frozen(pattern);
  }
  StringValue(rewrite);
  rewrite = rb_str_new_frozen(rewrite);

  /* Take a copy of str so it can be modified in-place by
   * RE2::GlobalReplace.
   */
  std::string str_as_string(RSTRING_PTR(str), RSTRING_LEN(str));

  nogvl_replace_arg arg;
  arg.str = &str_as_string;
  if (p) {
    arg.pattern = p->pattern;
  } else {
    arg.pattern = nullptr;
    arg.string_pattern = re2::StringPiece(
        RSTRING_PTR(pattern), RSTRING_LEN(pattern));
  }
  arg.rewrite = re2::StringPiece(
      RSTRING_PTR(rewrite), RSTRING_LEN(rewrite));

#ifdef _WIN32
  nogvl_global_replace(&arg);
#else
  rb_thread_call_without_gvl(nogvl_global_replace, &arg, NULL, NULL);
#endif

  RB_GC_GUARD(rewrite);
  RB_GC_GUARD(pattern);

  if (p) {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        p->pattern->options().encoding());
  } else {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        RE2::Options::EncodingUTF8);
  }
}

.GlobalReplace(str, pattern, rewrite) ⇒ String

Return a copy of str with pattern replaced by rewrite using `GlobalReplace`.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

re2 = RE2::Regexp.new("oo?")
RE2.global_replace("whoops-doops", re2, "e") #=> "wheps-deps"
RE2.global_replace("hello there", "e", "i")  #=> "hillo thiri"

Parameters:

  • str (String) —

    the string to modify

  • pattern (String, RE2::Regexp) —

    a regexp matching text to be replaced

  • rewrite (String) —

    the string to replace with

Returns:

  • (String) —

    the resulting string

Raises:

  • (TypeError) —

    if the given rewrite or pattern (if not provided as a Regexp) cannot be coerced to Strings



2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
 
# File 'ext/re2/re2.cc', line 2311

static VALUE re2_global_replace(VALUE, VALUE str, VALUE pattern,
                               VALUE rewrite) {
  re2_pattern *p = nullptr;

  /* Coerce and freeze all arguments before any C++ allocations so that any
   * Ruby exceptions (via longjmp) cannot bypass C++ destructors and leak
   * memory, and later coercions cannot mutate earlier strings.
   */
  StringValue(str);
  str = rb_str_new_frozen(str);
  if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
    p = unwrap_re2_regexp(pattern);
  } else {
    StringValue(pattern);
    pattern = rb_str_new_frozen(pattern);
  }
  StringValue(rewrite);
  rewrite = rb_str_new_frozen(rewrite);

  /* Take a copy of str so it can be modified in-place by
   * RE2::GlobalReplace.
   */
  std::string str_as_string(RSTRING_PTR(str), RSTRING_LEN(str));

  nogvl_replace_arg arg;
  arg.str = &str_as_string;
  if (p) {
    arg.pattern = p->pattern;
  } else {
    arg.pattern = nullptr;
    arg.string_pattern = re2::StringPiece(
        RSTRING_PTR(pattern), RSTRING_LEN(pattern));
  }
  arg.rewrite = re2::StringPiece(
      RSTRING_PTR(rewrite), RSTRING_LEN(rewrite));

#ifdef _WIN32
  nogvl_global_replace(&arg);
#else
  rb_thread_call_without_gvl(nogvl_global_replace, &arg, NULL, NULL);
#endif

  RB_GC_GUARD(rewrite);
  RB_GC_GUARD(pattern);

  if (p) {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        p->pattern->options().encoding());
  } else {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        RE2::Options::EncodingUTF8);
  }
}

.quote(unquoted) ⇒ String

Returns a version of str with all potentially meaningful regexp characters escaped using `QuoteMeta`. The returned string, used as a regular expression, will exactly match the original string.

Examples:

RE2.escape("1.5-2.0?")         #=> "1\\.5\\-2\\.0\\?"
RE2.quote("1.5-2.0?")          #=> "1\\.5\\-2\\.0\\?"
RE2::Regexp.escape("1.5-2.0?") #=> "1\\.5\\-2\\.0\\?"
RE2::Regexp.quote("1.5-2.0?")  #=> "1\\.5\\-2\\.0\\?"

Parameters:

  • unquoted (String) —

    the unquoted string

Returns:

  • (String) —

    the escaped string

Raises:

  • (TypeError) —

    if the given unquoted string cannot be coerced to a String



2457
2458
2459
2460
2461
2462
2463
2464
 
# File 'ext/re2/re2.cc', line 2457

static VALUE re2_escape(VALUE, VALUE unquoted) {
  StringValue(unquoted);

  std::string quoted_string = RE2::QuoteMeta(
      re2::StringPiece(RSTRING_PTR(unquoted), RSTRING_LEN(unquoted)));

  return rb_str_new(quoted_string.data(), quoted_string.size());
}

.QuoteMeta(unquoted) ⇒ String

Returns a version of str with all potentially meaningful regexp characters escaped using `QuoteMeta`. The returned string, used as a regular expression, will exactly match the original string.

Examples:

RE2.escape("1.5-2.0?")         #=> "1\\.5\\-2\\.0\\?"
RE2.quote("1.5-2.0?")          #=> "1\\.5\\-2\\.0\\?"
RE2::Regexp.escape("1.5-2.0?") #=> "1\\.5\\-2\\.0\\?"
RE2::Regexp.quote("1.5-2.0?")  #=> "1\\.5\\-2\\.0\\?"

Parameters:

  • unquoted (String) —

    the unquoted string

Returns:

  • (String) —

    the escaped string

Raises:

  • (TypeError) —

    if the given unquoted string cannot be coerced to a String



2457
2458
2459
2460
2461
2462
2463
2464
 
# File 'ext/re2/re2.cc', line 2457

static VALUE re2_escape(VALUE, VALUE unquoted) {
  StringValue(unquoted);

  std::string quoted_string = RE2::QuoteMeta(
      re2::StringPiece(RSTRING_PTR(unquoted), RSTRING_LEN(unquoted)));

  return rb_str_new(quoted_string.data(), quoted_string.size());
}

.replace(str, pattern, rewrite) ⇒ String

Returns a copy of str with the first occurrence pattern replaced with rewrite using `Replace`.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

RE2.replace("hello there", "hello", "howdy") #=> "howdy there"
re2 = RE2::Regexp.new("hel+o")
RE2.replace("hello there", re2, "yo")        #=> "yo there"

Parameters:

  • str (String) —

    the string to modify

  • pattern (String, RE2::Regexp) —

    a regexp matching text to be replaced

  • rewrite (String) —

    the string to replace with

Returns:

  • (String) —

    the resulting string

Raises:

  • (TypeError) —

    if the given rewrite or pattern (if not provided as a Regexp) cannot be coerced to Strings



2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
 
# File 'ext/re2/re2.cc', line 2239

static VALUE re2_replace(VALUE, VALUE str, VALUE pattern,
    VALUE rewrite) {
  re2_pattern *p = nullptr;

  /* Coerce and freeze all arguments before any C++ allocations so that any
   * Ruby exceptions (via longjmp) cannot bypass C++ destructors and leak
   * memory, and later coercions cannot mutate earlier strings.
   */
  StringValue(str);
  str = rb_str_new_frozen(str);
  if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
    p = unwrap_re2_regexp(pattern);
  } else {
    StringValue(pattern);
    pattern = rb_str_new_frozen(pattern);
  }
  StringValue(rewrite);
  rewrite = rb_str_new_frozen(rewrite);

  /* Take a copy of str so it can be modified in-place by RE2::Replace. */
  std::string str_as_string(RSTRING_PTR(str), RSTRING_LEN(str));

  nogvl_replace_arg arg;
  arg.str = &str_as_string;
  if (p) {
    arg.pattern = p->pattern;
  } else {
    arg.pattern = nullptr;
    arg.string_pattern = re2::StringPiece(
        RSTRING_PTR(pattern), RSTRING_LEN(pattern));
  }
  arg.rewrite = re2::StringPiece(
      RSTRING_PTR(rewrite), RSTRING_LEN(rewrite));

#ifdef _WIN32
  nogvl_replace(&arg);
#else
  rb_thread_call_without_gvl(nogvl_replace, &arg, NULL, NULL);
#endif

  RB_GC_GUARD(rewrite);
  RB_GC_GUARD(pattern);

  if (p) {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        p->pattern->options().encoding());
  } else {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        RE2::Options::EncodingUTF8);
  }
}

.Replace(str, pattern, rewrite) ⇒ String

Returns a copy of str with the first occurrence pattern replaced with rewrite using `Replace`.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

RE2.replace("hello there", "hello", "howdy") #=> "howdy there"
re2 = RE2::Regexp.new("hel+o")
RE2.replace("hello there", re2, "yo")        #=> "yo there"

Parameters:

  • str (String) —

    the string to modify

  • pattern (String, RE2::Regexp) —

    a regexp matching text to be replaced

  • rewrite (String) —

    the string to replace with

Returns:

  • (String) —

    the resulting string

Raises:

  • (TypeError) —

    if the given rewrite or pattern (if not provided as a Regexp) cannot be coerced to Strings



2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
 
# File 'ext/re2/re2.cc', line 2239

static VALUE re2_replace(VALUE, VALUE str, VALUE pattern,
    VALUE rewrite) {
  re2_pattern *p = nullptr;

  /* Coerce and freeze all arguments before any C++ allocations so that any
   * Ruby exceptions (via longjmp) cannot bypass C++ destructors and leak
   * memory, and later coercions cannot mutate earlier strings.
   */
  StringValue(str);
  str = rb_str_new_frozen(str);
  if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
    p = unwrap_re2_regexp(pattern);
  } else {
    StringValue(pattern);
    pattern = rb_str_new_frozen(pattern);
  }
  StringValue(rewrite);
  rewrite = rb_str_new_frozen(rewrite);

  /* Take a copy of str so it can be modified in-place by RE2::Replace. */
  std::string str_as_string(RSTRING_PTR(str), RSTRING_LEN(str));

  nogvl_replace_arg arg;
  arg.str = &str_as_string;
  if (p) {
    arg.pattern = p->pattern;
  } else {
    arg.pattern = nullptr;
    arg.string_pattern = re2::StringPiece(
        RSTRING_PTR(pattern), RSTRING_LEN(pattern));
  }
  arg.rewrite = re2::StringPiece(
      RSTRING_PTR(rewrite), RSTRING_LEN(rewrite));

#ifdef _WIN32
  nogvl_replace(&arg);
#else
  rb_thread_call_without_gvl(nogvl_replace, &arg, NULL, NULL);
#endif

  RB_GC_GUARD(rewrite);
  RB_GC_GUARD(pattern);

  if (p) {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        p->pattern->options().encoding());
  } else {
    return encoded_str_new(str_as_string.data(), str_as_string.size(),
        RE2::Options::EncodingUTF8);
  }
}