duckdb 0.4.1-dev439.0 → 0.4.1-dev454.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
- package/src/duckdb.cpp +170 -1307
- package/src/duckdb.hpp +1223 -4
- package/src/parquet-amalgamation.cpp +36822 -36651
- package/src/parquet-amalgamation.hpp +2 -0
package/src/duckdb.cpp
CHANGED
|
@@ -8075,7 +8075,7 @@ ParameterNotResolvedException::ParameterNotResolvedException()
|
|
|
8075
8075
|
|
|
8076
8076
|
|
|
8077
8077
|
// LICENSE_CHANGE_BEGIN
|
|
8078
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
8078
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #2
|
|
8079
8079
|
// See the end of this file for a list
|
|
8080
8080
|
|
|
8081
8081
|
/*
|
|
@@ -8117,7 +8117,7 @@ ParameterNotResolvedException::ParameterNotResolvedException()
|
|
|
8117
8117
|
|
|
8118
8118
|
|
|
8119
8119
|
// LICENSE_CHANGE_BEGIN
|
|
8120
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
8120
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #2
|
|
8121
8121
|
// See the end of this file for a list
|
|
8122
8122
|
|
|
8123
8123
|
// Formatting library for C++ - the core API
|
|
@@ -12901,7 +12901,7 @@ FMT_END_NAMESPACE
|
|
|
12901
12901
|
|
|
12902
12902
|
|
|
12903
12903
|
// LICENSE_CHANGE_BEGIN
|
|
12904
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
12904
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #2
|
|
12905
12905
|
// See the end of this file for a list
|
|
12906
12906
|
|
|
12907
12907
|
// Formatting library for C++ - legacy printf implementation
|
|
@@ -12920,7 +12920,7 @@ FMT_END_NAMESPACE
|
|
|
12920
12920
|
|
|
12921
12921
|
|
|
12922
12922
|
// LICENSE_CHANGE_BEGIN
|
|
12923
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
12923
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #2
|
|
12924
12924
|
// See the end of this file for a list
|
|
12925
12925
|
|
|
12926
12926
|
// Formatting library for C++ - std::ostream support
|
|
@@ -14081,7 +14081,7 @@ void FileBuffer::Clear() {
|
|
|
14081
14081
|
|
|
14082
14082
|
|
|
14083
14083
|
// LICENSE_CHANGE_BEGIN
|
|
14084
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
14084
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #3
|
|
14085
14085
|
// See the end of this file for a list
|
|
14086
14086
|
|
|
14087
14087
|
/*
|
|
@@ -15421,7 +15421,7 @@ static constexpr const unsigned char GZIP_FLAG_UNSUPPORTED =
|
|
|
15421
15421
|
|
|
15422
15422
|
|
|
15423
15423
|
// LICENSE_CHANGE_BEGIN
|
|
15424
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
15424
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #4
|
|
15425
15425
|
// See the end of this file for a list
|
|
15426
15426
|
|
|
15427
15427
|
/* miniz.c 2.0.8 - public domain deflate/inflate, zlib-subset, ZIP reading/writing/appending, PNG writing
|
|
@@ -16719,7 +16719,7 @@ void *mz_zip_extract_archive_file_to_heap_v2(const char *pZip_filename, const ch
|
|
|
16719
16719
|
|
|
16720
16720
|
|
|
16721
16721
|
// LICENSE_CHANGE_BEGIN
|
|
16722
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
16722
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #4
|
|
16723
16723
|
// See the end of this file for a list
|
|
16724
16724
|
|
|
16725
16725
|
//===----------------------------------------------------------------------===//
|
|
@@ -20770,7 +20770,7 @@ struct IntervalToStringCast {
|
|
|
20770
20770
|
|
|
20771
20771
|
|
|
20772
20772
|
// LICENSE_CHANGE_BEGIN
|
|
20773
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
20773
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #5
|
|
20774
20774
|
// See the end of this file for a list
|
|
20775
20775
|
|
|
20776
20776
|
// duckdb_fast_float by Daniel Lemire
|
|
@@ -26048,7 +26048,7 @@ private:
|
|
|
26048
26048
|
|
|
26049
26049
|
|
|
26050
26050
|
// LICENSE_CHANGE_BEGIN
|
|
26051
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
26051
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #6
|
|
26052
26052
|
// See the end of this file for a list
|
|
26053
26053
|
|
|
26054
26054
|
/*
|
|
@@ -26175,7 +26175,7 @@ private:
|
|
|
26175
26175
|
|
|
26176
26176
|
|
|
26177
26177
|
// LICENSE_CHANGE_BEGIN
|
|
26178
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
26178
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #6
|
|
26179
26179
|
// See the end of this file for a list
|
|
26180
26180
|
|
|
26181
26181
|
/*
|
|
@@ -26264,7 +26264,7 @@ private:
|
|
|
26264
26264
|
|
|
26265
26265
|
|
|
26266
26266
|
// LICENSE_CHANGE_BEGIN
|
|
26267
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
26267
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #6
|
|
26268
26268
|
// See the end of this file for a list
|
|
26269
26269
|
|
|
26270
26270
|
/*
|
|
@@ -29692,1191 +29692,6 @@ DUCKDB_API std::vector<Match> RegexFindAll(const std::string &input, const Regex
|
|
|
29692
29692
|
|
|
29693
29693
|
|
|
29694
29694
|
|
|
29695
|
-
// LICENSE_CHANGE_BEGIN
|
|
29696
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #6
|
|
29697
|
-
// See the end of this file for a list
|
|
29698
|
-
|
|
29699
|
-
// Copyright 2003-2009 The RE2 Authors. All Rights Reserved.
|
|
29700
|
-
// Use of this source code is governed by a BSD-style
|
|
29701
|
-
// license that can be found in the LICENSE file.
|
|
29702
|
-
|
|
29703
|
-
#ifndef RE2_RE2_H_
|
|
29704
|
-
#define RE2_RE2_H_
|
|
29705
|
-
|
|
29706
|
-
// C++ interface to the re2 regular-expression library.
|
|
29707
|
-
// RE2 supports Perl-style regular expressions (with extensions like
|
|
29708
|
-
// \d, \w, \s, ...).
|
|
29709
|
-
//
|
|
29710
|
-
// -----------------------------------------------------------------------
|
|
29711
|
-
// REGEXP SYNTAX:
|
|
29712
|
-
//
|
|
29713
|
-
// This module uses the re2 library and hence supports
|
|
29714
|
-
// its syntax for regular expressions, which is similar to Perl's with
|
|
29715
|
-
// some of the more complicated things thrown away. In particular,
|
|
29716
|
-
// backreferences and generalized assertions are not available, nor is \Z.
|
|
29717
|
-
//
|
|
29718
|
-
// See https://github.com/google/re2/wiki/Syntax for the syntax
|
|
29719
|
-
// supported by RE2, and a comparison with PCRE and PERL regexps.
|
|
29720
|
-
//
|
|
29721
|
-
// For those not familiar with Perl's regular expressions,
|
|
29722
|
-
// here are some examples of the most commonly used extensions:
|
|
29723
|
-
//
|
|
29724
|
-
// "hello (\\w+) world" -- \w matches a "word" character
|
|
29725
|
-
// "version (\\d+)" -- \d matches a digit
|
|
29726
|
-
// "hello\\s+world" -- \s matches any whitespace character
|
|
29727
|
-
// "\\b(\\w+)\\b" -- \b matches non-empty string at word boundary
|
|
29728
|
-
// "(?i)hello" -- (?i) turns on case-insensitive matching
|
|
29729
|
-
// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible
|
|
29730
|
-
//
|
|
29731
|
-
// -----------------------------------------------------------------------
|
|
29732
|
-
// MATCHING INTERFACE:
|
|
29733
|
-
//
|
|
29734
|
-
// The "FullMatch" operation checks that supplied text matches a
|
|
29735
|
-
// supplied pattern exactly.
|
|
29736
|
-
//
|
|
29737
|
-
// Example: successful match
|
|
29738
|
-
// CHECK(RE2::FullMatch("hello", "h.*o"));
|
|
29739
|
-
//
|
|
29740
|
-
// Example: unsuccessful match (requires full match):
|
|
29741
|
-
// CHECK(!RE2::FullMatch("hello", "e"));
|
|
29742
|
-
//
|
|
29743
|
-
// -----------------------------------------------------------------------
|
|
29744
|
-
// UTF-8 AND THE MATCHING INTERFACE:
|
|
29745
|
-
//
|
|
29746
|
-
// By default, the pattern and input text are interpreted as UTF-8.
|
|
29747
|
-
// The RE2::Latin1 option causes them to be interpreted as Latin-1.
|
|
29748
|
-
//
|
|
29749
|
-
// Example:
|
|
29750
|
-
// CHECK(RE2::FullMatch(utf8_string, RE2(utf8_pattern)));
|
|
29751
|
-
// CHECK(RE2::FullMatch(latin1_string, RE2(latin1_pattern, RE2::Latin1)));
|
|
29752
|
-
//
|
|
29753
|
-
// -----------------------------------------------------------------------
|
|
29754
|
-
// MATCHING WITH SUBSTRING EXTRACTION:
|
|
29755
|
-
//
|
|
29756
|
-
// You can supply extra pointer arguments to extract matched substrings.
|
|
29757
|
-
// On match failure, none of the pointees will have been modified.
|
|
29758
|
-
// On match success, the substrings will be converted (as necessary) and
|
|
29759
|
-
// their values will be assigned to their pointees until all conversions
|
|
29760
|
-
// have succeeded or one conversion has failed.
|
|
29761
|
-
// On conversion failure, the pointees will be in an indeterminate state
|
|
29762
|
-
// because the caller has no way of knowing which conversion failed.
|
|
29763
|
-
// However, conversion cannot fail for types like string and StringPiece
|
|
29764
|
-
// that do not inspect the substring contents. Hence, in the common case
|
|
29765
|
-
// where all of the pointees are of such types, failure is always due to
|
|
29766
|
-
// match failure and thus none of the pointees will have been modified.
|
|
29767
|
-
//
|
|
29768
|
-
// Example: extracts "ruby" into "s" and 1234 into "i"
|
|
29769
|
-
// int i;
|
|
29770
|
-
// std::string s;
|
|
29771
|
-
// CHECK(RE2::FullMatch("ruby:1234", "(\\w+):(\\d+)", &s, &i));
|
|
29772
|
-
//
|
|
29773
|
-
// Example: fails because string cannot be stored in integer
|
|
29774
|
-
// CHECK(!RE2::FullMatch("ruby", "(.*)", &i));
|
|
29775
|
-
//
|
|
29776
|
-
// Example: fails because there aren't enough sub-patterns
|
|
29777
|
-
// CHECK(!RE2::FullMatch("ruby:1234", "\\w+:\\d+", &s));
|
|
29778
|
-
//
|
|
29779
|
-
// Example: does not try to extract any extra sub-patterns
|
|
29780
|
-
// CHECK(RE2::FullMatch("ruby:1234", "(\\w+):(\\d+)", &s));
|
|
29781
|
-
//
|
|
29782
|
-
// Example: does not try to extract into NULL
|
|
29783
|
-
// CHECK(RE2::FullMatch("ruby:1234", "(\\w+):(\\d+)", NULL, &i));
|
|
29784
|
-
//
|
|
29785
|
-
// Example: integer overflow causes failure
|
|
29786
|
-
// CHECK(!RE2::FullMatch("ruby:1234567891234", "\\w+:(\\d+)", &i));
|
|
29787
|
-
//
|
|
29788
|
-
// NOTE(rsc): Asking for substrings slows successful matches quite a bit.
|
|
29789
|
-
// This may get a little faster in the future, but right now is slower
|
|
29790
|
-
// than PCRE. On the other hand, failed matches run *very* fast (faster
|
|
29791
|
-
// than PCRE), as do matches without substring extraction.
|
|
29792
|
-
//
|
|
29793
|
-
// -----------------------------------------------------------------------
|
|
29794
|
-
// PARTIAL MATCHES
|
|
29795
|
-
//
|
|
29796
|
-
// You can use the "PartialMatch" operation when you want the pattern
|
|
29797
|
-
// to match any substring of the text.
|
|
29798
|
-
//
|
|
29799
|
-
// Example: simple search for a string:
|
|
29800
|
-
// CHECK(RE2::PartialMatch("hello", "ell"));
|
|
29801
|
-
//
|
|
29802
|
-
// Example: find first number in a string
|
|
29803
|
-
// int number;
|
|
29804
|
-
// CHECK(RE2::PartialMatch("x*100 + 20", "(\\d+)", &number));
|
|
29805
|
-
// CHECK_EQ(number, 100);
|
|
29806
|
-
//
|
|
29807
|
-
// -----------------------------------------------------------------------
|
|
29808
|
-
// PRE-COMPILED REGULAR EXPRESSIONS
|
|
29809
|
-
//
|
|
29810
|
-
// RE2 makes it easy to use any string as a regular expression, without
|
|
29811
|
-
// requiring a separate compilation step.
|
|
29812
|
-
//
|
|
29813
|
-
// If speed is of the essence, you can create a pre-compiled "RE2"
|
|
29814
|
-
// object from the pattern and use it multiple times. If you do so,
|
|
29815
|
-
// you can typically parse text faster than with sscanf.
|
|
29816
|
-
//
|
|
29817
|
-
// Example: precompile pattern for faster matching:
|
|
29818
|
-
// RE2 pattern("h.*o");
|
|
29819
|
-
// while (ReadLine(&str)) {
|
|
29820
|
-
// if (RE2::FullMatch(str, pattern)) ...;
|
|
29821
|
-
// }
|
|
29822
|
-
//
|
|
29823
|
-
// -----------------------------------------------------------------------
|
|
29824
|
-
// SCANNING TEXT INCREMENTALLY
|
|
29825
|
-
//
|
|
29826
|
-
// The "Consume" operation may be useful if you want to repeatedly
|
|
29827
|
-
// match regular expressions at the front of a string and skip over
|
|
29828
|
-
// them as they match. This requires use of the "StringPiece" type,
|
|
29829
|
-
// which represents a sub-range of a real string.
|
|
29830
|
-
//
|
|
29831
|
-
// Example: read lines of the form "var = value" from a string.
|
|
29832
|
-
// std::string contents = ...; // Fill string somehow
|
|
29833
|
-
// StringPiece input(contents); // Wrap a StringPiece around it
|
|
29834
|
-
//
|
|
29835
|
-
// std::string var;
|
|
29836
|
-
// int value;
|
|
29837
|
-
// while (RE2::Consume(&input, "(\\w+) = (\\d+)\n", &var, &value)) {
|
|
29838
|
-
// ...;
|
|
29839
|
-
// }
|
|
29840
|
-
//
|
|
29841
|
-
// Each successful call to "Consume" will set "var/value", and also
|
|
29842
|
-
// advance "input" so it points past the matched text. Note that if the
|
|
29843
|
-
// regular expression matches an empty string, input will advance
|
|
29844
|
-
// by 0 bytes. If the regular expression being used might match
|
|
29845
|
-
// an empty string, the loop body must check for this case and either
|
|
29846
|
-
// advance the string or break out of the loop.
|
|
29847
|
-
//
|
|
29848
|
-
// The "FindAndConsume" operation is similar to "Consume" but does not
|
|
29849
|
-
// anchor your match at the beginning of the string. For example, you
|
|
29850
|
-
// could extract all words from a string by repeatedly calling
|
|
29851
|
-
// RE2::FindAndConsume(&input, "(\\w+)", &word)
|
|
29852
|
-
//
|
|
29853
|
-
// -----------------------------------------------------------------------
|
|
29854
|
-
// USING VARIABLE NUMBER OF ARGUMENTS
|
|
29855
|
-
//
|
|
29856
|
-
// The above operations require you to know the number of arguments
|
|
29857
|
-
// when you write the code. This is not always possible or easy (for
|
|
29858
|
-
// example, the regular expression may be calculated at run time).
|
|
29859
|
-
// You can use the "N" version of the operations when the number of
|
|
29860
|
-
// match arguments are determined at run time.
|
|
29861
|
-
//
|
|
29862
|
-
// Example:
|
|
29863
|
-
// const RE2::Arg* args[10];
|
|
29864
|
-
// int n;
|
|
29865
|
-
// // ... populate args with pointers to RE2::Arg values ...
|
|
29866
|
-
// // ... set n to the number of RE2::Arg objects ...
|
|
29867
|
-
// bool match = RE2::FullMatchN(input, pattern, args, n);
|
|
29868
|
-
//
|
|
29869
|
-
// The last statement is equivalent to
|
|
29870
|
-
//
|
|
29871
|
-
// bool match = RE2::FullMatch(input, pattern,
|
|
29872
|
-
// *args[0], *args[1], ..., *args[n - 1]);
|
|
29873
|
-
//
|
|
29874
|
-
// -----------------------------------------------------------------------
|
|
29875
|
-
// PARSING HEX/OCTAL/C-RADIX NUMBERS
|
|
29876
|
-
//
|
|
29877
|
-
// By default, if you pass a pointer to a numeric value, the
|
|
29878
|
-
// corresponding text is interpreted as a base-10 number. You can
|
|
29879
|
-
// instead wrap the pointer with a call to one of the operators Hex(),
|
|
29880
|
-
// Octal(), or CRadix() to interpret the text in another base. The
|
|
29881
|
-
// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16)
|
|
29882
|
-
// prefixes, but defaults to base-10.
|
|
29883
|
-
//
|
|
29884
|
-
// Example:
|
|
29885
|
-
// int a, b, c, d;
|
|
29886
|
-
// CHECK(RE2::FullMatch("100 40 0100 0x40", "(.*) (.*) (.*) (.*)",
|
|
29887
|
-
// RE2::Octal(&a), RE2::Hex(&b), RE2::CRadix(&c), RE2::CRadix(&d));
|
|
29888
|
-
// will leave 64 in a, b, c, and d.
|
|
29889
|
-
|
|
29890
|
-
#include <stddef.h>
|
|
29891
|
-
#include <stdint.h>
|
|
29892
|
-
#include <algorithm>
|
|
29893
|
-
#include <map>
|
|
29894
|
-
#include <mutex>
|
|
29895
|
-
#include <string>
|
|
29896
|
-
|
|
29897
|
-
|
|
29898
|
-
|
|
29899
|
-
// LICENSE_CHANGE_BEGIN
|
|
29900
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #6
|
|
29901
|
-
// See the end of this file for a list
|
|
29902
|
-
|
|
29903
|
-
// Copyright 2001-2010 The RE2 Authors. All Rights Reserved.
|
|
29904
|
-
// Use of this source code is governed by a BSD-style
|
|
29905
|
-
// license that can be found in the LICENSE file.
|
|
29906
|
-
|
|
29907
|
-
#ifndef RE2_STRINGPIECE_H_
|
|
29908
|
-
#define RE2_STRINGPIECE_H_
|
|
29909
|
-
|
|
29910
|
-
#ifdef min
|
|
29911
|
-
#undef min
|
|
29912
|
-
#endif
|
|
29913
|
-
|
|
29914
|
-
// A string-like object that points to a sized piece of memory.
|
|
29915
|
-
//
|
|
29916
|
-
// Functions or methods may use const StringPiece& parameters to accept either
|
|
29917
|
-
// a "const char*" or a "string" value that will be implicitly converted to
|
|
29918
|
-
// a StringPiece. The implicit conversion means that it is often appropriate
|
|
29919
|
-
// to include this .h file in other files rather than forward-declaring
|
|
29920
|
-
// StringPiece as would be appropriate for most other Google classes.
|
|
29921
|
-
//
|
|
29922
|
-
// Systematic usage of StringPiece is encouraged as it will reduce unnecessary
|
|
29923
|
-
// conversions from "const char*" to "string" and back again.
|
|
29924
|
-
//
|
|
29925
|
-
//
|
|
29926
|
-
// Arghh! I wish C++ literals were "string".
|
|
29927
|
-
|
|
29928
|
-
// Doing this simplifies the logic below.
|
|
29929
|
-
#ifndef __has_include
|
|
29930
|
-
#define __has_include(x) 0
|
|
29931
|
-
#endif
|
|
29932
|
-
|
|
29933
|
-
#include <stddef.h>
|
|
29934
|
-
#include <string.h>
|
|
29935
|
-
#include <algorithm>
|
|
29936
|
-
#include <iosfwd>
|
|
29937
|
-
#include <iterator>
|
|
29938
|
-
#include <string>
|
|
29939
|
-
#if __has_include(<string_view>) && __cplusplus >= 201703L
|
|
29940
|
-
#include <string_view>
|
|
29941
|
-
#endif
|
|
29942
|
-
|
|
29943
|
-
namespace duckdb_re2 {
|
|
29944
|
-
|
|
29945
|
-
class StringPiece {
|
|
29946
|
-
public:
|
|
29947
|
-
typedef std::char_traits<char> traits_type;
|
|
29948
|
-
typedef char value_type;
|
|
29949
|
-
typedef char* pointer;
|
|
29950
|
-
typedef const char* const_pointer;
|
|
29951
|
-
typedef char& reference;
|
|
29952
|
-
typedef const char& const_reference;
|
|
29953
|
-
typedef const char* const_iterator;
|
|
29954
|
-
typedef const_iterator iterator;
|
|
29955
|
-
typedef std::reverse_iterator<const_iterator> const_reverse_iterator;
|
|
29956
|
-
typedef const_reverse_iterator reverse_iterator;
|
|
29957
|
-
typedef size_t size_type;
|
|
29958
|
-
typedef ptrdiff_t difference_type;
|
|
29959
|
-
static const size_type npos = static_cast<size_type>(-1);
|
|
29960
|
-
|
|
29961
|
-
// We provide non-explicit singleton constructors so users can pass
|
|
29962
|
-
// in a "const char*" or a "string" wherever a "StringPiece" is
|
|
29963
|
-
// expected.
|
|
29964
|
-
StringPiece()
|
|
29965
|
-
: data_(NULL), size_(0) {}
|
|
29966
|
-
#if __has_include(<string_view>) && __cplusplus >= 201703L
|
|
29967
|
-
StringPiece(const std::string_view& str)
|
|
29968
|
-
: data_(str.data()), size_(str.size()) {}
|
|
29969
|
-
#endif
|
|
29970
|
-
StringPiece(const std::string& str)
|
|
29971
|
-
: data_(str.data()), size_(str.size()) {}
|
|
29972
|
-
StringPiece(const char* str)
|
|
29973
|
-
: data_(str), size_(str == NULL ? 0 : strlen(str)) {}
|
|
29974
|
-
StringPiece(const char* str, size_type len)
|
|
29975
|
-
: data_(str), size_(len) {}
|
|
29976
|
-
|
|
29977
|
-
const_iterator begin() const { return data_; }
|
|
29978
|
-
const_iterator end() const { return data_ + size_; }
|
|
29979
|
-
const_reverse_iterator rbegin() const {
|
|
29980
|
-
return const_reverse_iterator(data_ + size_);
|
|
29981
|
-
}
|
|
29982
|
-
const_reverse_iterator rend() const {
|
|
29983
|
-
return const_reverse_iterator(data_);
|
|
29984
|
-
}
|
|
29985
|
-
|
|
29986
|
-
size_type size() const { return size_; }
|
|
29987
|
-
size_type length() const { return size_; }
|
|
29988
|
-
bool empty() const { return size_ == 0; }
|
|
29989
|
-
|
|
29990
|
-
const_reference operator[](size_type i) const { return data_[i]; }
|
|
29991
|
-
const_pointer data() const { return data_; }
|
|
29992
|
-
|
|
29993
|
-
void remove_prefix(size_type n) {
|
|
29994
|
-
data_ += n;
|
|
29995
|
-
size_ -= n;
|
|
29996
|
-
}
|
|
29997
|
-
|
|
29998
|
-
void remove_suffix(size_type n) {
|
|
29999
|
-
size_ -= n;
|
|
30000
|
-
}
|
|
30001
|
-
|
|
30002
|
-
void set(const char* str) {
|
|
30003
|
-
data_ = str;
|
|
30004
|
-
size_ = str == NULL ? 0 : strlen(str);
|
|
30005
|
-
}
|
|
30006
|
-
|
|
30007
|
-
void set(const char* str, size_type len) {
|
|
30008
|
-
data_ = str;
|
|
30009
|
-
size_ = len;
|
|
30010
|
-
}
|
|
30011
|
-
|
|
30012
|
-
// Converts to `std::basic_string`.
|
|
30013
|
-
template <typename A>
|
|
30014
|
-
explicit operator std::basic_string<char, traits_type, A>() const {
|
|
30015
|
-
if (!data_) return {};
|
|
30016
|
-
return std::basic_string<char, traits_type, A>(data_, size_);
|
|
30017
|
-
}
|
|
30018
|
-
|
|
30019
|
-
std::string as_string() const {
|
|
30020
|
-
return std::string(data_, size_);
|
|
30021
|
-
}
|
|
30022
|
-
|
|
30023
|
-
// We also define ToString() here, since many other string-like
|
|
30024
|
-
// interfaces name the routine that converts to a C++ string
|
|
30025
|
-
// "ToString", and it's confusing to have the method that does that
|
|
30026
|
-
// for a StringPiece be called "as_string()". We also leave the
|
|
30027
|
-
// "as_string()" method defined here for existing code.
|
|
30028
|
-
std::string ToString() const {
|
|
30029
|
-
return std::string(data_, size_);
|
|
30030
|
-
}
|
|
30031
|
-
|
|
30032
|
-
void CopyToString(std::string* target) const {
|
|
30033
|
-
target->assign(data_, size_);
|
|
30034
|
-
}
|
|
30035
|
-
|
|
30036
|
-
void AppendToString(std::string* target) const {
|
|
30037
|
-
target->append(data_, size_);
|
|
30038
|
-
}
|
|
30039
|
-
|
|
30040
|
-
size_type copy(char* buf, size_type n, size_type pos = 0) const;
|
|
30041
|
-
StringPiece substr(size_type pos = 0, size_type n = npos) const;
|
|
30042
|
-
|
|
30043
|
-
int compare(const StringPiece& x) const {
|
|
30044
|
-
size_type min_size = std::min(size(), x.size());
|
|
30045
|
-
if (min_size > 0) {
|
|
30046
|
-
int r = memcmp(data(), x.data(), min_size);
|
|
30047
|
-
if (r < 0) return -1;
|
|
30048
|
-
if (r > 0) return 1;
|
|
30049
|
-
}
|
|
30050
|
-
if (size() < x.size()) return -1;
|
|
30051
|
-
if (size() > x.size()) return 1;
|
|
30052
|
-
return 0;
|
|
30053
|
-
}
|
|
30054
|
-
|
|
30055
|
-
// Does "this" start with "x"?
|
|
30056
|
-
bool starts_with(const StringPiece& x) const {
|
|
30057
|
-
return x.empty() ||
|
|
30058
|
-
(size() >= x.size() && memcmp(data(), x.data(), x.size()) == 0);
|
|
30059
|
-
}
|
|
30060
|
-
|
|
30061
|
-
// Does "this" end with "x"?
|
|
30062
|
-
bool ends_with(const StringPiece& x) const {
|
|
30063
|
-
return x.empty() ||
|
|
30064
|
-
(size() >= x.size() &&
|
|
30065
|
-
memcmp(data() + (size() - x.size()), x.data(), x.size()) == 0);
|
|
30066
|
-
}
|
|
30067
|
-
|
|
30068
|
-
bool contains(const StringPiece& s) const {
|
|
30069
|
-
return find(s) != npos;
|
|
30070
|
-
}
|
|
30071
|
-
|
|
30072
|
-
size_type find(const StringPiece& s, size_type pos = 0) const;
|
|
30073
|
-
size_type find(char c, size_type pos = 0) const;
|
|
30074
|
-
size_type rfind(const StringPiece& s, size_type pos = npos) const;
|
|
30075
|
-
size_type rfind(char c, size_type pos = npos) const;
|
|
30076
|
-
|
|
30077
|
-
private:
|
|
30078
|
-
const_pointer data_;
|
|
30079
|
-
size_type size_;
|
|
30080
|
-
};
|
|
30081
|
-
|
|
30082
|
-
inline bool operator==(const StringPiece& x, const StringPiece& y) {
|
|
30083
|
-
StringPiece::size_type len = x.size();
|
|
30084
|
-
if (len != y.size()) return false;
|
|
30085
|
-
return x.data() == y.data() || len == 0 ||
|
|
30086
|
-
memcmp(x.data(), y.data(), len) == 0;
|
|
30087
|
-
}
|
|
30088
|
-
|
|
30089
|
-
inline bool operator!=(const StringPiece& x, const StringPiece& y) {
|
|
30090
|
-
return !(x == y);
|
|
30091
|
-
}
|
|
30092
|
-
|
|
30093
|
-
inline bool operator<(const StringPiece& x, const StringPiece& y) {
|
|
30094
|
-
StringPiece::size_type min_size = std::min(x.size(), y.size());
|
|
30095
|
-
int r = min_size == 0 ? 0 : memcmp(x.data(), y.data(), min_size);
|
|
30096
|
-
return (r < 0) || (r == 0 && x.size() < y.size());
|
|
30097
|
-
}
|
|
30098
|
-
|
|
30099
|
-
inline bool operator>(const StringPiece& x, const StringPiece& y) {
|
|
30100
|
-
return y < x;
|
|
30101
|
-
}
|
|
30102
|
-
|
|
30103
|
-
inline bool operator<=(const StringPiece& x, const StringPiece& y) {
|
|
30104
|
-
return !(x > y);
|
|
30105
|
-
}
|
|
30106
|
-
|
|
30107
|
-
inline bool operator>=(const StringPiece& x, const StringPiece& y) {
|
|
30108
|
-
return !(x < y);
|
|
30109
|
-
}
|
|
30110
|
-
|
|
30111
|
-
// Allow StringPiece to be logged.
|
|
30112
|
-
std::ostream& operator<<(std::ostream& o, const StringPiece& p);
|
|
30113
|
-
|
|
30114
|
-
} // namespace duckdb_re2
|
|
30115
|
-
|
|
30116
|
-
#endif // RE2_STRINGPIECE_H_
|
|
30117
|
-
|
|
30118
|
-
|
|
30119
|
-
// LICENSE_CHANGE_END
|
|
30120
|
-
|
|
30121
|
-
|
|
30122
|
-
namespace duckdb_re2 {
|
|
30123
|
-
class Prog;
|
|
30124
|
-
class Regexp;
|
|
30125
|
-
} // namespace duckdb_re2
|
|
30126
|
-
|
|
30127
|
-
namespace duckdb_re2 {
|
|
30128
|
-
|
|
30129
|
-
// Interface for regular expression matching. Also corresponds to a
|
|
30130
|
-
// pre-compiled regular expression. An "RE2" object is safe for
|
|
30131
|
-
// concurrent use by multiple threads.
|
|
30132
|
-
class RE2 {
|
|
30133
|
-
public:
|
|
30134
|
-
// We convert user-passed pointers into special Arg objects
|
|
30135
|
-
class Arg;
|
|
30136
|
-
class Options;
|
|
30137
|
-
|
|
30138
|
-
// Defined in set.h.
|
|
30139
|
-
class Set;
|
|
30140
|
-
|
|
30141
|
-
enum ErrorCode {
|
|
30142
|
-
NoError = 0,
|
|
30143
|
-
|
|
30144
|
-
// Unexpected error
|
|
30145
|
-
ErrorInternal,
|
|
30146
|
-
|
|
30147
|
-
// Parse errors
|
|
30148
|
-
ErrorBadEscape, // bad escape sequence
|
|
30149
|
-
ErrorBadCharClass, // bad character class
|
|
30150
|
-
ErrorBadCharRange, // bad character class range
|
|
30151
|
-
ErrorMissingBracket, // missing closing ]
|
|
30152
|
-
ErrorMissingParen, // missing closing )
|
|
30153
|
-
ErrorTrailingBackslash, // trailing \ at end of regexp
|
|
30154
|
-
ErrorRepeatArgument, // repeat argument missing, e.g. "*"
|
|
30155
|
-
ErrorRepeatSize, // bad repetition argument
|
|
30156
|
-
ErrorRepeatOp, // bad repetition operator
|
|
30157
|
-
ErrorBadPerlOp, // bad perl operator
|
|
30158
|
-
ErrorBadUTF8, // invalid UTF-8 in regexp
|
|
30159
|
-
ErrorBadNamedCapture, // bad named capture group
|
|
30160
|
-
ErrorPatternTooLarge // pattern too large (compile failed)
|
|
30161
|
-
};
|
|
30162
|
-
|
|
30163
|
-
// Predefined common options.
|
|
30164
|
-
// If you need more complicated things, instantiate
|
|
30165
|
-
// an Option class, possibly passing one of these to
|
|
30166
|
-
// the Option constructor, change the settings, and pass that
|
|
30167
|
-
// Option class to the RE2 constructor.
|
|
30168
|
-
enum CannedOptions {
|
|
30169
|
-
DefaultOptions = 0,
|
|
30170
|
-
Latin1, // treat input as Latin-1 (default UTF-8)
|
|
30171
|
-
POSIX, // POSIX syntax, leftmost-longest match
|
|
30172
|
-
Quiet // do not log about regexp parse errors
|
|
30173
|
-
};
|
|
30174
|
-
|
|
30175
|
-
// Need to have the const char* and const std::string& forms for implicit
|
|
30176
|
-
// conversions when passing string literals to FullMatch and PartialMatch.
|
|
30177
|
-
// Otherwise the StringPiece form would be sufficient.
|
|
30178
|
-
#ifndef SWIG
|
|
30179
|
-
RE2(const char* pattern);
|
|
30180
|
-
RE2(const std::string& pattern);
|
|
30181
|
-
#endif
|
|
30182
|
-
RE2(const StringPiece& pattern);
|
|
30183
|
-
RE2(const StringPiece& pattern, const Options& options);
|
|
30184
|
-
~RE2();
|
|
30185
|
-
|
|
30186
|
-
// Returns whether RE2 was created properly.
|
|
30187
|
-
bool ok() const { return error_code() == NoError; }
|
|
30188
|
-
|
|
30189
|
-
// The string specification for this RE2. E.g.
|
|
30190
|
-
// RE2 re("ab*c?d+");
|
|
30191
|
-
// re.pattern(); // "ab*c?d+"
|
|
30192
|
-
const std::string& pattern() const { return pattern_; }
|
|
30193
|
-
|
|
30194
|
-
// If RE2 could not be created properly, returns an error string.
|
|
30195
|
-
// Else returns the empty string.
|
|
30196
|
-
const std::string& error() const { return *error_; }
|
|
30197
|
-
|
|
30198
|
-
// If RE2 could not be created properly, returns an error code.
|
|
30199
|
-
// Else returns RE2::NoError (== 0).
|
|
30200
|
-
ErrorCode error_code() const { return error_code_; }
|
|
30201
|
-
|
|
30202
|
-
// If RE2 could not be created properly, returns the offending
|
|
30203
|
-
// portion of the regexp.
|
|
30204
|
-
const std::string& error_arg() const { return error_arg_; }
|
|
30205
|
-
|
|
30206
|
-
// Returns the program size, a very approximate measure of a regexp's "cost".
|
|
30207
|
-
// Larger numbers are more expensive than smaller numbers.
|
|
30208
|
-
int ProgramSize() const;
|
|
30209
|
-
int ReverseProgramSize() const;
|
|
30210
|
-
|
|
30211
|
-
// EXPERIMENTAL! SUBJECT TO CHANGE!
|
|
30212
|
-
// Outputs the program fanout as a histogram bucketed by powers of 2.
|
|
30213
|
-
// Returns the number of the largest non-empty bucket.
|
|
30214
|
-
int ProgramFanout(std::map<int, int>* histogram) const;
|
|
30215
|
-
int ReverseProgramFanout(std::map<int, int>* histogram) const;
|
|
30216
|
-
|
|
30217
|
-
// Returns the underlying Regexp; not for general use.
|
|
30218
|
-
// Returns entire_regexp_ so that callers don't need
|
|
30219
|
-
// to know about prefix_ and prefix_foldcase_.
|
|
30220
|
-
duckdb_re2::Regexp* Regexp() const { return entire_regexp_; }
|
|
30221
|
-
|
|
30222
|
-
/***** The array-based matching interface ******/
|
|
30223
|
-
|
|
30224
|
-
// The functions here have names ending in 'N' and are used to implement
|
|
30225
|
-
// the functions whose names are the prefix before the 'N'. It is sometimes
|
|
30226
|
-
// useful to invoke them directly, but the syntax is awkward, so the 'N'-less
|
|
30227
|
-
// versions should be preferred.
|
|
30228
|
-
static bool FullMatchN(const StringPiece& text, const RE2& re,
|
|
30229
|
-
const Arg* const args[], int n);
|
|
30230
|
-
static bool PartialMatchN(const StringPiece& text, const RE2& re,
|
|
30231
|
-
const Arg* const args[], int n);
|
|
30232
|
-
static bool ConsumeN(StringPiece* input, const RE2& re,
|
|
30233
|
-
const Arg* const args[], int n);
|
|
30234
|
-
static bool FindAndConsumeN(StringPiece* input, const RE2& re,
|
|
30235
|
-
const Arg* const args[], int n);
|
|
30236
|
-
|
|
30237
|
-
#ifndef SWIG
|
|
30238
|
-
private:
|
|
30239
|
-
template <typename F, typename SP>
|
|
30240
|
-
static inline bool Apply(F f, SP sp, const RE2& re) {
|
|
30241
|
-
return f(sp, re, NULL, 0);
|
|
30242
|
-
}
|
|
30243
|
-
|
|
30244
|
-
template <typename F, typename SP, typename... A>
|
|
30245
|
-
static inline bool Apply(F f, SP sp, const RE2& re, const A&... a) {
|
|
30246
|
-
const Arg* const args[] = {&a...};
|
|
30247
|
-
const int n = sizeof...(a);
|
|
30248
|
-
return f(sp, re, args, n);
|
|
30249
|
-
}
|
|
30250
|
-
|
|
30251
|
-
public:
|
|
30252
|
-
// In order to allow FullMatch() et al. to be called with a varying number
|
|
30253
|
-
// of arguments of varying types, we use two layers of variadic templates.
|
|
30254
|
-
// The first layer constructs the temporary Arg objects. The second layer
|
|
30255
|
-
// (above) constructs the array of pointers to the temporary Arg objects.
|
|
30256
|
-
|
|
30257
|
-
/***** The useful part: the matching interface *****/
|
|
30258
|
-
|
|
30259
|
-
// Matches "text" against "re". If pointer arguments are
|
|
30260
|
-
// supplied, copies matched sub-patterns into them.
|
|
30261
|
-
//
|
|
30262
|
-
// You can pass in a "const char*" or a "std::string" for "text".
|
|
30263
|
-
// You can pass in a "const char*" or a "std::string" or a "RE2" for "re".
|
|
30264
|
-
//
|
|
30265
|
-
// The provided pointer arguments can be pointers to any scalar numeric
|
|
30266
|
-
// type, or one of:
|
|
30267
|
-
// std::string (matched piece is copied to string)
|
|
30268
|
-
// StringPiece (StringPiece is mutated to point to matched piece)
|
|
30269
|
-
// T (where "bool T::ParseFrom(const char*, size_t)" exists)
|
|
30270
|
-
// (void*)NULL (the corresponding matched sub-pattern is not copied)
|
|
30271
|
-
//
|
|
30272
|
-
// Returns true iff all of the following conditions are satisfied:
|
|
30273
|
-
// a. "text" matches "re" exactly
|
|
30274
|
-
// b. The number of matched sub-patterns is >= number of supplied pointers
|
|
30275
|
-
// c. The "i"th argument has a suitable type for holding the
|
|
30276
|
-
// string captured as the "i"th sub-pattern. If you pass in
|
|
30277
|
-
// NULL for the "i"th argument, or pass fewer arguments than
|
|
30278
|
-
// number of sub-patterns, "i"th captured sub-pattern is
|
|
30279
|
-
// ignored.
|
|
30280
|
-
//
|
|
30281
|
-
// CAVEAT: An optional sub-pattern that does not exist in the
|
|
30282
|
-
// matched string is assigned the empty string. Therefore, the
|
|
30283
|
-
// following will return false (because the empty string is not a
|
|
30284
|
-
// valid number):
|
|
30285
|
-
// int number;
|
|
30286
|
-
// RE2::FullMatch("abc", "[a-z]+(\\d+)?", &number);
|
|
30287
|
-
template <typename... A>
|
|
30288
|
-
static bool FullMatch(const StringPiece& text, const RE2& re, A&&... a) {
|
|
30289
|
-
return Apply(FullMatchN, text, re, Arg(std::forward<A>(a))...);
|
|
30290
|
-
}
|
|
30291
|
-
|
|
30292
|
-
// Exactly like FullMatch(), except that "re" is allowed to match
|
|
30293
|
-
// a substring of "text".
|
|
30294
|
-
template <typename... A>
|
|
30295
|
-
static bool PartialMatch(const StringPiece& text, const RE2& re, A&&... a) {
|
|
30296
|
-
return Apply(PartialMatchN, text, re, Arg(std::forward<A>(a))...);
|
|
30297
|
-
}
|
|
30298
|
-
|
|
30299
|
-
// Like FullMatch() and PartialMatch(), except that "re" has to match
|
|
30300
|
-
// a prefix of the text, and "input" is advanced past the matched
|
|
30301
|
-
// text. Note: "input" is modified iff this routine returns true
|
|
30302
|
-
// and "re" matched a non-empty substring of "text".
|
|
30303
|
-
template <typename... A>
|
|
30304
|
-
static bool Consume(StringPiece* input, const RE2& re, A&&... a) {
|
|
30305
|
-
return Apply(ConsumeN, input, re, Arg(std::forward<A>(a))...);
|
|
30306
|
-
}
|
|
30307
|
-
|
|
30308
|
-
// Like Consume(), but does not anchor the match at the beginning of
|
|
30309
|
-
// the text. That is, "re" need not start its match at the beginning
|
|
30310
|
-
// of "input". For example, "FindAndConsume(s, "(\\w+)", &word)" finds
|
|
30311
|
-
// the next word in "s" and stores it in "word".
|
|
30312
|
-
template <typename... A>
|
|
30313
|
-
static bool FindAndConsume(StringPiece* input, const RE2& re, A&&... a) {
|
|
30314
|
-
return Apply(FindAndConsumeN, input, re, Arg(std::forward<A>(a))...);
|
|
30315
|
-
}
|
|
30316
|
-
#endif
|
|
30317
|
-
|
|
30318
|
-
// Replace the first match of "re" in "str" with "rewrite".
|
|
30319
|
-
// Within "rewrite", backslash-escaped digits (\1 to \9) can be
|
|
30320
|
-
// used to insert text matching corresponding parenthesized group
|
|
30321
|
-
// from the pattern. \0 in "rewrite" refers to the entire matching
|
|
30322
|
-
// text. E.g.,
|
|
30323
|
-
//
|
|
30324
|
-
// std::string s = "yabba dabba doo";
|
|
30325
|
-
// CHECK(RE2::Replace(&s, "b+", "d"));
|
|
30326
|
-
//
|
|
30327
|
-
// will leave "s" containing "yada dabba doo"
|
|
30328
|
-
//
|
|
30329
|
-
// Returns true if the pattern matches and a replacement occurs,
|
|
30330
|
-
// false otherwise.
|
|
30331
|
-
static bool Replace(std::string* str,
|
|
30332
|
-
const RE2& re,
|
|
30333
|
-
const StringPiece& rewrite);
|
|
30334
|
-
|
|
30335
|
-
// Like Replace(), except replaces successive non-overlapping occurrences
|
|
30336
|
-
// of the pattern in the string with the rewrite. E.g.
|
|
30337
|
-
//
|
|
30338
|
-
// std::string s = "yabba dabba doo";
|
|
30339
|
-
// CHECK(RE2::GlobalReplace(&s, "b+", "d"));
|
|
30340
|
-
//
|
|
30341
|
-
// will leave "s" containing "yada dada doo"
|
|
30342
|
-
// Replacements are not subject to re-matching.
|
|
30343
|
-
//
|
|
30344
|
-
// Because GlobalReplace only replaces non-overlapping matches,
|
|
30345
|
-
// replacing "ana" within "banana" makes only one replacement, not two.
|
|
30346
|
-
//
|
|
30347
|
-
// Returns the number of replacements made.
|
|
30348
|
-
static int GlobalReplace(std::string* str,
|
|
30349
|
-
const RE2& re,
|
|
30350
|
-
const StringPiece& rewrite);
|
|
30351
|
-
|
|
30352
|
-
// Like Replace, except that if the pattern matches, "rewrite"
|
|
30353
|
-
// is copied into "out" with substitutions. The non-matching
|
|
30354
|
-
// portions of "text" are ignored.
|
|
30355
|
-
//
|
|
30356
|
-
// Returns true iff a match occurred and the extraction happened
|
|
30357
|
-
// successfully; if no match occurs, the string is left unaffected.
|
|
30358
|
-
//
|
|
30359
|
-
// REQUIRES: "text" must not alias any part of "*out".
|
|
30360
|
-
static bool Extract(const StringPiece& text,
|
|
30361
|
-
const RE2& re,
|
|
30362
|
-
const StringPiece& rewrite,
|
|
30363
|
-
std::string* out);
|
|
30364
|
-
|
|
30365
|
-
// Escapes all potentially meaningful regexp characters in
|
|
30366
|
-
// 'unquoted'. The returned string, used as a regular expression,
|
|
30367
|
-
// will exactly match the original string. For example,
|
|
30368
|
-
// 1.5-2.0?
|
|
30369
|
-
// may become:
|
|
30370
|
-
// 1\.5\-2\.0\?
|
|
30371
|
-
static std::string QuoteMeta(const StringPiece& unquoted);
|
|
30372
|
-
|
|
30373
|
-
// Computes range for any strings matching regexp. The min and max can in
|
|
30374
|
-
// some cases be arbitrarily precise, so the caller gets to specify the
|
|
30375
|
-
// maximum desired length of string returned.
|
|
30376
|
-
//
|
|
30377
|
-
// Assuming PossibleMatchRange(&min, &max, N) returns successfully, any
|
|
30378
|
-
// string s that is an anchored match for this regexp satisfies
|
|
30379
|
-
// min <= s && s <= max.
|
|
30380
|
-
//
|
|
30381
|
-
// Note that PossibleMatchRange() will only consider the first copy of an
|
|
30382
|
-
// infinitely repeated element (i.e., any regexp element followed by a '*' or
|
|
30383
|
-
// '+' operator). Regexps with "{N}" constructions are not affected, as those
|
|
30384
|
-
// do not compile down to infinite repetitions.
|
|
30385
|
-
//
|
|
30386
|
-
// Returns true on success, false on error.
|
|
30387
|
-
bool PossibleMatchRange(std::string* min, std::string* max,
|
|
30388
|
-
int maxlen) const;
|
|
30389
|
-
|
|
30390
|
-
// Generic matching interface
|
|
30391
|
-
|
|
30392
|
-
// Type of match.
|
|
30393
|
-
enum Anchor {
|
|
30394
|
-
UNANCHORED, // No anchoring
|
|
30395
|
-
ANCHOR_START, // Anchor at start only
|
|
30396
|
-
ANCHOR_BOTH // Anchor at start and end
|
|
30397
|
-
};
|
|
30398
|
-
|
|
30399
|
-
// Return the number of capturing subpatterns, or -1 if the
|
|
30400
|
-
// regexp wasn't valid on construction. The overall match ($0)
|
|
30401
|
-
// does not count: if the regexp is "(a)(b)", returns 2.
|
|
30402
|
-
int NumberOfCapturingGroups() const { return num_captures_; }
|
|
30403
|
-
|
|
30404
|
-
// Return a map from names to capturing indices.
|
|
30405
|
-
// The map records the index of the leftmost group
|
|
30406
|
-
// with the given name.
|
|
30407
|
-
// Only valid until the re is deleted.
|
|
30408
|
-
const std::map<std::string, int>& NamedCapturingGroups() const;
|
|
30409
|
-
|
|
30410
|
-
// Return a map from capturing indices to names.
|
|
30411
|
-
// The map has no entries for unnamed groups.
|
|
30412
|
-
// Only valid until the re is deleted.
|
|
30413
|
-
const std::map<int, std::string>& CapturingGroupNames() const;
|
|
30414
|
-
|
|
30415
|
-
// General matching routine.
|
|
30416
|
-
// Match against text starting at offset startpos
|
|
30417
|
-
// and stopping the search at offset endpos.
|
|
30418
|
-
// Returns true if match found, false if not.
|
|
30419
|
-
// On a successful match, fills in submatch[] (up to nsubmatch entries)
|
|
30420
|
-
// with information about submatches.
|
|
30421
|
-
// I.e. matching RE2("(foo)|(bar)baz") on "barbazbla" will return true, with
|
|
30422
|
-
// submatch[0] = "barbaz", submatch[1].data() = NULL, submatch[2] = "bar",
|
|
30423
|
-
// submatch[3].data() = NULL, ..., up to submatch[nsubmatch-1].data() = NULL.
|
|
30424
|
-
// Caveat: submatch[] may be clobbered even on match failure.
|
|
30425
|
-
//
|
|
30426
|
-
// Don't ask for more match information than you will use:
|
|
30427
|
-
// runs much faster with nsubmatch == 1 than nsubmatch > 1, and
|
|
30428
|
-
// runs even faster if nsubmatch == 0.
|
|
30429
|
-
// Doesn't make sense to use nsubmatch > 1 + NumberOfCapturingGroups(),
|
|
30430
|
-
// but will be handled correctly.
|
|
30431
|
-
//
|
|
30432
|
-
// Passing text == StringPiece(NULL, 0) will be handled like any other
|
|
30433
|
-
// empty string, but note that on return, it will not be possible to tell
|
|
30434
|
-
// whether submatch i matched the empty string or did not match:
|
|
30435
|
-
// either way, submatch[i].data() == NULL.
|
|
30436
|
-
bool Match(const StringPiece& text,
|
|
30437
|
-
size_t startpos,
|
|
30438
|
-
size_t endpos,
|
|
30439
|
-
Anchor re_anchor,
|
|
30440
|
-
StringPiece* submatch,
|
|
30441
|
-
int nsubmatch) const;
|
|
30442
|
-
|
|
30443
|
-
// Check that the given rewrite string is suitable for use with this
|
|
30444
|
-
// regular expression. It checks that:
|
|
30445
|
-
// * The regular expression has enough parenthesized subexpressions
|
|
30446
|
-
// to satisfy all of the \N tokens in rewrite
|
|
30447
|
-
// * The rewrite string doesn't have any syntax errors. E.g.,
|
|
30448
|
-
// '\' followed by anything other than a digit or '\'.
|
|
30449
|
-
// A true return value guarantees that Replace() and Extract() won't
|
|
30450
|
-
// fail because of a bad rewrite string.
|
|
30451
|
-
bool CheckRewriteString(const StringPiece& rewrite,
|
|
30452
|
-
std::string* error) const;
|
|
30453
|
-
|
|
30454
|
-
// Returns the maximum submatch needed for the rewrite to be done by
|
|
30455
|
-
// Replace(). E.g. if rewrite == "foo \\2,\\1", returns 2.
|
|
30456
|
-
static int MaxSubmatch(const StringPiece& rewrite);
|
|
30457
|
-
|
|
30458
|
-
// Append the "rewrite" string, with backslash subsitutions from "vec",
|
|
30459
|
-
// to string "out".
|
|
30460
|
-
// Returns true on success. This method can fail because of a malformed
|
|
30461
|
-
// rewrite string. CheckRewriteString guarantees that the rewrite will
|
|
30462
|
-
// be sucessful.
|
|
30463
|
-
bool Rewrite(std::string* out,
|
|
30464
|
-
const StringPiece& rewrite,
|
|
30465
|
-
const StringPiece* vec,
|
|
30466
|
-
int veclen) const;
|
|
30467
|
-
|
|
30468
|
-
// Constructor options
|
|
30469
|
-
class Options {
|
|
30470
|
-
public:
|
|
30471
|
-
// The options are (defaults in parentheses):
|
|
30472
|
-
//
|
|
30473
|
-
// utf8 (true) text and pattern are UTF-8; otherwise Latin-1
|
|
30474
|
-
// posix_syntax (false) restrict regexps to POSIX egrep syntax
|
|
30475
|
-
// longest_match (false) search for longest match, not first match
|
|
30476
|
-
// log_errors (true) log syntax and execution errors to ERROR
|
|
30477
|
-
// max_mem (see below) approx. max memory footprint of RE2
|
|
30478
|
-
// literal (false) interpret string as literal, not regexp
|
|
30479
|
-
// never_nl (false) never match \n, even if it is in regexp
|
|
30480
|
-
// dot_nl (false) dot matches everything including new line
|
|
30481
|
-
// never_capture (false) parse all parens as non-capturing
|
|
30482
|
-
// case_sensitive (true) match is case-sensitive (regexp can override
|
|
30483
|
-
// with (?i) unless in posix_syntax mode)
|
|
30484
|
-
//
|
|
30485
|
-
// The following options are only consulted when posix_syntax == true.
|
|
30486
|
-
// When posix_syntax == false, these features are always enabled and
|
|
30487
|
-
// cannot be turned off; to perform multi-line matching in that case,
|
|
30488
|
-
// begin the regexp with (?m).
|
|
30489
|
-
// perl_classes (false) allow Perl's \d \s \w \D \S \W
|
|
30490
|
-
// word_boundary (false) allow Perl's \b \B (word boundary and not)
|
|
30491
|
-
// one_line (false) ^ and $ only match beginning and end of text
|
|
30492
|
-
//
|
|
30493
|
-
// The max_mem option controls how much memory can be used
|
|
30494
|
-
// to hold the compiled form of the regexp (the Prog) and
|
|
30495
|
-
// its cached DFA graphs. Code Search placed limits on the number
|
|
30496
|
-
// of Prog instructions and DFA states: 10,000 for both.
|
|
30497
|
-
// In RE2, those limits would translate to about 240 KB per Prog
|
|
30498
|
-
// and perhaps 2.5 MB per DFA (DFA state sizes vary by regexp; RE2 does a
|
|
30499
|
-
// better job of keeping them small than Code Search did).
|
|
30500
|
-
// Each RE2 has two Progs (one forward, one reverse), and each Prog
|
|
30501
|
-
// can have two DFAs (one first match, one longest match).
|
|
30502
|
-
// That makes 4 DFAs:
|
|
30503
|
-
//
|
|
30504
|
-
// forward, first-match - used for UNANCHORED or ANCHOR_START searches
|
|
30505
|
-
// if opt.longest_match() == false
|
|
30506
|
-
// forward, longest-match - used for all ANCHOR_BOTH searches,
|
|
30507
|
-
// and the other two kinds if
|
|
30508
|
-
// opt.longest_match() == true
|
|
30509
|
-
// reverse, first-match - never used
|
|
30510
|
-
// reverse, longest-match - used as second phase for unanchored searches
|
|
30511
|
-
//
|
|
30512
|
-
// The RE2 memory budget is statically divided between the two
|
|
30513
|
-
// Progs and then the DFAs: two thirds to the forward Prog
|
|
30514
|
-
// and one third to the reverse Prog. The forward Prog gives half
|
|
30515
|
-
// of what it has left over to each of its DFAs. The reverse Prog
|
|
30516
|
-
// gives it all to its longest-match DFA.
|
|
30517
|
-
//
|
|
30518
|
-
// Once a DFA fills its budget, it flushes its cache and starts over.
|
|
30519
|
-
// If this happens too often, RE2 falls back on the NFA implementation.
|
|
30520
|
-
|
|
30521
|
-
// For now, make the default budget something close to Code Search.
|
|
30522
|
-
static const int kDefaultMaxMem = 8<<20;
|
|
30523
|
-
|
|
30524
|
-
enum Encoding {
|
|
30525
|
-
EncodingUTF8 = 1,
|
|
30526
|
-
EncodingLatin1
|
|
30527
|
-
};
|
|
30528
|
-
|
|
30529
|
-
Options() :
|
|
30530
|
-
encoding_(EncodingUTF8),
|
|
30531
|
-
posix_syntax_(false),
|
|
30532
|
-
longest_match_(false),
|
|
30533
|
-
log_errors_(true),
|
|
30534
|
-
max_mem_(kDefaultMaxMem),
|
|
30535
|
-
literal_(false),
|
|
30536
|
-
never_nl_(false),
|
|
30537
|
-
dot_nl_(false),
|
|
30538
|
-
never_capture_(false),
|
|
30539
|
-
case_sensitive_(true),
|
|
30540
|
-
perl_classes_(false),
|
|
30541
|
-
word_boundary_(false),
|
|
30542
|
-
one_line_(false) {
|
|
30543
|
-
}
|
|
30544
|
-
|
|
30545
|
-
/*implicit*/ Options(CannedOptions);
|
|
30546
|
-
|
|
30547
|
-
Encoding encoding() const { return encoding_; }
|
|
30548
|
-
void set_encoding(Encoding encoding) { encoding_ = encoding; }
|
|
30549
|
-
|
|
30550
|
-
// Legacy interface to encoding.
|
|
30551
|
-
// TODO(rsc): Remove once clients have been converted.
|
|
30552
|
-
bool utf8() const { return encoding_ == EncodingUTF8; }
|
|
30553
|
-
void set_utf8(bool b) {
|
|
30554
|
-
if (b) {
|
|
30555
|
-
encoding_ = EncodingUTF8;
|
|
30556
|
-
} else {
|
|
30557
|
-
encoding_ = EncodingLatin1;
|
|
30558
|
-
}
|
|
30559
|
-
}
|
|
30560
|
-
|
|
30561
|
-
bool posix_syntax() const { return posix_syntax_; }
|
|
30562
|
-
void set_posix_syntax(bool b) { posix_syntax_ = b; }
|
|
30563
|
-
|
|
30564
|
-
bool longest_match() const { return longest_match_; }
|
|
30565
|
-
void set_longest_match(bool b) { longest_match_ = b; }
|
|
30566
|
-
|
|
30567
|
-
bool log_errors() const { return log_errors_; }
|
|
30568
|
-
void set_log_errors(bool b) { log_errors_ = b; }
|
|
30569
|
-
|
|
30570
|
-
int64_t max_mem() const { return max_mem_; }
|
|
30571
|
-
void set_max_mem(int64_t m) { max_mem_ = m; }
|
|
30572
|
-
|
|
30573
|
-
bool literal() const { return literal_; }
|
|
30574
|
-
void set_literal(bool b) { literal_ = b; }
|
|
30575
|
-
|
|
30576
|
-
bool never_nl() const { return never_nl_; }
|
|
30577
|
-
void set_never_nl(bool b) { never_nl_ = b; }
|
|
30578
|
-
|
|
30579
|
-
bool dot_nl() const { return dot_nl_; }
|
|
30580
|
-
void set_dot_nl(bool b) { dot_nl_ = b; }
|
|
30581
|
-
|
|
30582
|
-
bool never_capture() const { return never_capture_; }
|
|
30583
|
-
void set_never_capture(bool b) { never_capture_ = b; }
|
|
30584
|
-
|
|
30585
|
-
bool case_sensitive() const { return case_sensitive_; }
|
|
30586
|
-
void set_case_sensitive(bool b) { case_sensitive_ = b; }
|
|
30587
|
-
|
|
30588
|
-
bool perl_classes() const { return perl_classes_; }
|
|
30589
|
-
void set_perl_classes(bool b) { perl_classes_ = b; }
|
|
30590
|
-
|
|
30591
|
-
bool word_boundary() const { return word_boundary_; }
|
|
30592
|
-
void set_word_boundary(bool b) { word_boundary_ = b; }
|
|
30593
|
-
|
|
30594
|
-
bool one_line() const { return one_line_; }
|
|
30595
|
-
void set_one_line(bool b) { one_line_ = b; }
|
|
30596
|
-
|
|
30597
|
-
void Copy(const Options& src) {
|
|
30598
|
-
*this = src;
|
|
30599
|
-
}
|
|
30600
|
-
|
|
30601
|
-
int ParseFlags() const;
|
|
30602
|
-
|
|
30603
|
-
private:
|
|
30604
|
-
Encoding encoding_;
|
|
30605
|
-
bool posix_syntax_;
|
|
30606
|
-
bool longest_match_;
|
|
30607
|
-
bool log_errors_;
|
|
30608
|
-
int64_t max_mem_;
|
|
30609
|
-
bool literal_;
|
|
30610
|
-
bool never_nl_;
|
|
30611
|
-
bool dot_nl_;
|
|
30612
|
-
bool never_capture_;
|
|
30613
|
-
bool case_sensitive_;
|
|
30614
|
-
bool perl_classes_;
|
|
30615
|
-
bool word_boundary_;
|
|
30616
|
-
bool one_line_;
|
|
30617
|
-
};
|
|
30618
|
-
|
|
30619
|
-
// Returns the options set in the constructor.
|
|
30620
|
-
const Options& options() const { return options_; }
|
|
30621
|
-
|
|
30622
|
-
// Argument converters; see below.
|
|
30623
|
-
static inline Arg CRadix(short* x);
|
|
30624
|
-
static inline Arg CRadix(unsigned short* x);
|
|
30625
|
-
static inline Arg CRadix(int* x);
|
|
30626
|
-
static inline Arg CRadix(unsigned int* x);
|
|
30627
|
-
static inline Arg CRadix(long* x);
|
|
30628
|
-
static inline Arg CRadix(unsigned long* x);
|
|
30629
|
-
static inline Arg CRadix(long long* x);
|
|
30630
|
-
static inline Arg CRadix(unsigned long long* x);
|
|
30631
|
-
|
|
30632
|
-
static inline Arg Hex(short* x);
|
|
30633
|
-
static inline Arg Hex(unsigned short* x);
|
|
30634
|
-
static inline Arg Hex(int* x);
|
|
30635
|
-
static inline Arg Hex(unsigned int* x);
|
|
30636
|
-
static inline Arg Hex(long* x);
|
|
30637
|
-
static inline Arg Hex(unsigned long* x);
|
|
30638
|
-
static inline Arg Hex(long long* x);
|
|
30639
|
-
static inline Arg Hex(unsigned long long* x);
|
|
30640
|
-
|
|
30641
|
-
static inline Arg Octal(short* x);
|
|
30642
|
-
static inline Arg Octal(unsigned short* x);
|
|
30643
|
-
static inline Arg Octal(int* x);
|
|
30644
|
-
static inline Arg Octal(unsigned int* x);
|
|
30645
|
-
static inline Arg Octal(long* x);
|
|
30646
|
-
static inline Arg Octal(unsigned long* x);
|
|
30647
|
-
static inline Arg Octal(long long* x);
|
|
30648
|
-
static inline Arg Octal(unsigned long long* x);
|
|
30649
|
-
|
|
30650
|
-
private:
|
|
30651
|
-
void Init(const StringPiece& pattern, const Options& options);
|
|
30652
|
-
|
|
30653
|
-
bool DoMatch(const StringPiece& text,
|
|
30654
|
-
Anchor re_anchor,
|
|
30655
|
-
size_t* consumed,
|
|
30656
|
-
const Arg* const args[],
|
|
30657
|
-
int n) const;
|
|
30658
|
-
|
|
30659
|
-
duckdb_re2::Prog* ReverseProg() const;
|
|
30660
|
-
|
|
30661
|
-
std::string pattern_; // string regular expression
|
|
30662
|
-
Options options_; // option flags
|
|
30663
|
-
std::string prefix_; // required prefix (before regexp_)
|
|
30664
|
-
bool prefix_foldcase_; // prefix is ASCII case-insensitive
|
|
30665
|
-
duckdb_re2::Regexp* entire_regexp_; // parsed regular expression
|
|
30666
|
-
duckdb_re2::Regexp* suffix_regexp_; // parsed regular expression, prefix removed
|
|
30667
|
-
duckdb_re2::Prog* prog_; // compiled program for regexp
|
|
30668
|
-
int num_captures_; // Number of capturing groups
|
|
30669
|
-
bool is_one_pass_; // can use prog_->SearchOnePass?
|
|
30670
|
-
|
|
30671
|
-
mutable duckdb_re2::Prog* rprog_; // reverse program for regexp
|
|
30672
|
-
mutable const std::string* error_; // Error indicator
|
|
30673
|
-
// (or points to empty string)
|
|
30674
|
-
mutable ErrorCode error_code_; // Error code
|
|
30675
|
-
mutable std::string error_arg_; // Fragment of regexp showing error
|
|
30676
|
-
|
|
30677
|
-
// Map from capture names to indices
|
|
30678
|
-
mutable const std::map<std::string, int>* named_groups_;
|
|
30679
|
-
|
|
30680
|
-
// Map from capture indices to names
|
|
30681
|
-
mutable const std::map<int, std::string>* group_names_;
|
|
30682
|
-
|
|
30683
|
-
// Onces for lazy computations.
|
|
30684
|
-
mutable std::once_flag rprog_once_;
|
|
30685
|
-
mutable std::once_flag named_groups_once_;
|
|
30686
|
-
mutable std::once_flag group_names_once_;
|
|
30687
|
-
|
|
30688
|
-
RE2(const RE2&) = delete;
|
|
30689
|
-
RE2& operator=(const RE2&) = delete;
|
|
30690
|
-
};
|
|
30691
|
-
|
|
30692
|
-
/***** Implementation details *****/
|
|
30693
|
-
|
|
30694
|
-
// Hex/Octal/Binary?
|
|
30695
|
-
|
|
30696
|
-
// Special class for parsing into objects that define a ParseFrom() method
|
|
30697
|
-
template <class T>
|
|
30698
|
-
class _RE2_MatchObject {
|
|
30699
|
-
public:
|
|
30700
|
-
static inline bool Parse(const char* str, size_t n, void* dest) {
|
|
30701
|
-
if (dest == NULL) return true;
|
|
30702
|
-
T* object = reinterpret_cast<T*>(dest);
|
|
30703
|
-
return object->ParseFrom(str, n);
|
|
30704
|
-
}
|
|
30705
|
-
};
|
|
30706
|
-
|
|
30707
|
-
class RE2::Arg {
|
|
30708
|
-
public:
|
|
30709
|
-
// Empty constructor so we can declare arrays of RE2::Arg
|
|
30710
|
-
Arg();
|
|
30711
|
-
|
|
30712
|
-
// Constructor specially designed for NULL arguments
|
|
30713
|
-
Arg(void*);
|
|
30714
|
-
Arg(std::nullptr_t);
|
|
30715
|
-
|
|
30716
|
-
typedef bool (*Parser)(const char* str, size_t n, void* dest);
|
|
30717
|
-
|
|
30718
|
-
// Type-specific parsers
|
|
30719
|
-
#define MAKE_PARSER(type, name) \
|
|
30720
|
-
Arg(type* p) : arg_(p), parser_(name) {} \
|
|
30721
|
-
Arg(type* p, Parser parser) : arg_(p), parser_(parser) {}
|
|
30722
|
-
|
|
30723
|
-
MAKE_PARSER(char, parse_char)
|
|
30724
|
-
MAKE_PARSER(signed char, parse_schar)
|
|
30725
|
-
MAKE_PARSER(unsigned char, parse_uchar)
|
|
30726
|
-
MAKE_PARSER(float, parse_float)
|
|
30727
|
-
MAKE_PARSER(double, parse_double)
|
|
30728
|
-
MAKE_PARSER(std::string, parse_string)
|
|
30729
|
-
MAKE_PARSER(StringPiece, parse_stringpiece)
|
|
30730
|
-
|
|
30731
|
-
MAKE_PARSER(short, parse_short)
|
|
30732
|
-
MAKE_PARSER(unsigned short, parse_ushort)
|
|
30733
|
-
MAKE_PARSER(int, parse_int)
|
|
30734
|
-
MAKE_PARSER(unsigned int, parse_uint)
|
|
30735
|
-
MAKE_PARSER(long, parse_long)
|
|
30736
|
-
MAKE_PARSER(unsigned long, parse_ulong)
|
|
30737
|
-
MAKE_PARSER(long long, parse_longlong)
|
|
30738
|
-
MAKE_PARSER(unsigned long long, parse_ulonglong)
|
|
30739
|
-
|
|
30740
|
-
#undef MAKE_PARSER
|
|
30741
|
-
|
|
30742
|
-
// Generic constructor templates
|
|
30743
|
-
template <class T> Arg(T* p)
|
|
30744
|
-
: arg_(p), parser_(_RE2_MatchObject<T>::Parse) { }
|
|
30745
|
-
template <class T> Arg(T* p, Parser parser)
|
|
30746
|
-
: arg_(p), parser_(parser) { }
|
|
30747
|
-
|
|
30748
|
-
// Parse the data
|
|
30749
|
-
bool Parse(const char* str, size_t n) const;
|
|
30750
|
-
|
|
30751
|
-
private:
|
|
30752
|
-
void* arg_;
|
|
30753
|
-
Parser parser_;
|
|
30754
|
-
|
|
30755
|
-
static bool parse_null (const char* str, size_t n, void* dest);
|
|
30756
|
-
static bool parse_char (const char* str, size_t n, void* dest);
|
|
30757
|
-
static bool parse_schar (const char* str, size_t n, void* dest);
|
|
30758
|
-
static bool parse_uchar (const char* str, size_t n, void* dest);
|
|
30759
|
-
static bool parse_float (const char* str, size_t n, void* dest);
|
|
30760
|
-
static bool parse_double (const char* str, size_t n, void* dest);
|
|
30761
|
-
static bool parse_string (const char* str, size_t n, void* dest);
|
|
30762
|
-
static bool parse_stringpiece (const char* str, size_t n, void* dest);
|
|
30763
|
-
|
|
30764
|
-
#define DECLARE_INTEGER_PARSER(name) \
|
|
30765
|
-
private: \
|
|
30766
|
-
static bool parse_##name(const char* str, size_t n, void* dest); \
|
|
30767
|
-
static bool parse_##name##_radix(const char* str, size_t n, void* dest, \
|
|
30768
|
-
int radix); \
|
|
30769
|
-
\
|
|
30770
|
-
public: \
|
|
30771
|
-
static bool parse_##name##_hex(const char* str, size_t n, void* dest); \
|
|
30772
|
-
static bool parse_##name##_octal(const char* str, size_t n, void* dest); \
|
|
30773
|
-
static bool parse_##name##_cradix(const char* str, size_t n, void* dest);
|
|
30774
|
-
|
|
30775
|
-
DECLARE_INTEGER_PARSER(short)
|
|
30776
|
-
DECLARE_INTEGER_PARSER(ushort)
|
|
30777
|
-
DECLARE_INTEGER_PARSER(int)
|
|
30778
|
-
DECLARE_INTEGER_PARSER(uint)
|
|
30779
|
-
DECLARE_INTEGER_PARSER(long)
|
|
30780
|
-
DECLARE_INTEGER_PARSER(ulong)
|
|
30781
|
-
DECLARE_INTEGER_PARSER(longlong)
|
|
30782
|
-
DECLARE_INTEGER_PARSER(ulonglong)
|
|
30783
|
-
|
|
30784
|
-
#undef DECLARE_INTEGER_PARSER
|
|
30785
|
-
|
|
30786
|
-
};
|
|
30787
|
-
|
|
30788
|
-
inline RE2::Arg::Arg() : arg_(NULL), parser_(parse_null) { }
|
|
30789
|
-
inline RE2::Arg::Arg(void* p) : arg_(p), parser_(parse_null) { }
|
|
30790
|
-
inline RE2::Arg::Arg(std::nullptr_t p) : arg_(p), parser_(parse_null) { }
|
|
30791
|
-
|
|
30792
|
-
inline bool RE2::Arg::Parse(const char* str, size_t n) const {
|
|
30793
|
-
return (*parser_)(str, n, arg_);
|
|
30794
|
-
}
|
|
30795
|
-
|
|
30796
|
-
// This part of the parser, appropriate only for ints, deals with bases
|
|
30797
|
-
#define MAKE_INTEGER_PARSER(type, name) \
|
|
30798
|
-
inline RE2::Arg RE2::Hex(type* ptr) { \
|
|
30799
|
-
return RE2::Arg(ptr, RE2::Arg::parse_##name##_hex); \
|
|
30800
|
-
} \
|
|
30801
|
-
inline RE2::Arg RE2::Octal(type* ptr) { \
|
|
30802
|
-
return RE2::Arg(ptr, RE2::Arg::parse_##name##_octal); \
|
|
30803
|
-
} \
|
|
30804
|
-
inline RE2::Arg RE2::CRadix(type* ptr) { \
|
|
30805
|
-
return RE2::Arg(ptr, RE2::Arg::parse_##name##_cradix); \
|
|
30806
|
-
}
|
|
30807
|
-
|
|
30808
|
-
MAKE_INTEGER_PARSER(short, short)
|
|
30809
|
-
MAKE_INTEGER_PARSER(unsigned short, ushort)
|
|
30810
|
-
MAKE_INTEGER_PARSER(int, int)
|
|
30811
|
-
MAKE_INTEGER_PARSER(unsigned int, uint)
|
|
30812
|
-
MAKE_INTEGER_PARSER(long, long)
|
|
30813
|
-
MAKE_INTEGER_PARSER(unsigned long, ulong)
|
|
30814
|
-
MAKE_INTEGER_PARSER(long long, longlong)
|
|
30815
|
-
MAKE_INTEGER_PARSER(unsigned long long, ulonglong)
|
|
30816
|
-
|
|
30817
|
-
#undef MAKE_INTEGER_PARSER
|
|
30818
|
-
|
|
30819
|
-
#ifndef SWIG
|
|
30820
|
-
|
|
30821
|
-
|
|
30822
|
-
// Helper for writing global or static RE2s safely.
|
|
30823
|
-
// Write
|
|
30824
|
-
// static LazyRE2 re = {".*"};
|
|
30825
|
-
// and then use *re instead of writing
|
|
30826
|
-
// static RE2 re(".*");
|
|
30827
|
-
// The former is more careful about multithreaded
|
|
30828
|
-
// situations than the latter.
|
|
30829
|
-
//
|
|
30830
|
-
// N.B. This class never deletes the RE2 object that
|
|
30831
|
-
// it constructs: that's a feature, so that it can be used
|
|
30832
|
-
// for global and function static variables.
|
|
30833
|
-
class LazyRE2 {
|
|
30834
|
-
private:
|
|
30835
|
-
struct NoArg {};
|
|
30836
|
-
|
|
30837
|
-
public:
|
|
30838
|
-
typedef RE2 element_type; // support std::pointer_traits
|
|
30839
|
-
|
|
30840
|
-
// Constructor omitted to preserve braced initialization in C++98.
|
|
30841
|
-
|
|
30842
|
-
// Pretend to be a pointer to Type (never NULL due to on-demand creation):
|
|
30843
|
-
RE2& operator*() const { return *get(); }
|
|
30844
|
-
RE2* operator->() const { return get(); }
|
|
30845
|
-
|
|
30846
|
-
// Named accessor/initializer:
|
|
30847
|
-
RE2* get() const {
|
|
30848
|
-
std::call_once(once_, &LazyRE2::Init, this);
|
|
30849
|
-
return ptr_;
|
|
30850
|
-
}
|
|
30851
|
-
|
|
30852
|
-
// All data fields must be public to support {"foo"} initialization.
|
|
30853
|
-
const char* pattern_;
|
|
30854
|
-
RE2::CannedOptions options_;
|
|
30855
|
-
NoArg barrier_against_excess_initializers_;
|
|
30856
|
-
|
|
30857
|
-
mutable RE2* ptr_;
|
|
30858
|
-
mutable std::once_flag once_;
|
|
30859
|
-
|
|
30860
|
-
private:
|
|
30861
|
-
static void Init(const LazyRE2* lazy_re2) {
|
|
30862
|
-
lazy_re2->ptr_ = new RE2(lazy_re2->pattern_, lazy_re2->options_);
|
|
30863
|
-
}
|
|
30864
|
-
|
|
30865
|
-
void operator=(const LazyRE2&); // disallowed
|
|
30866
|
-
};
|
|
30867
|
-
#endif // SWIG
|
|
30868
|
-
|
|
30869
|
-
} // namespace duckdb_re2
|
|
30870
|
-
|
|
30871
|
-
using duckdb_re2::RE2;
|
|
30872
|
-
using duckdb_re2::LazyRE2;
|
|
30873
|
-
|
|
30874
|
-
#endif // RE2_RE2_H_
|
|
30875
|
-
|
|
30876
|
-
|
|
30877
|
-
// LICENSE_CHANGE_END
|
|
30878
|
-
|
|
30879
|
-
|
|
30880
29695
|
namespace duckdb_re2 {
|
|
30881
29696
|
|
|
30882
29697
|
Regex::Regex(const std::string &pattern, RegexOptions options) {
|
|
@@ -37881,7 +36696,7 @@ public:
|
|
|
37881
36696
|
|
|
37882
36697
|
|
|
37883
36698
|
// LICENSE_CHANGE_BEGIN
|
|
37884
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
36699
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #3
|
|
37885
36700
|
// See the end of this file for a list
|
|
37886
36701
|
|
|
37887
36702
|
|
|
@@ -61486,34 +60301,41 @@ static void ComputeWindowExpression(BoundWindowExpression *wexpr, ChunkCollectio
|
|
|
61486
60301
|
}
|
|
61487
60302
|
case ExpressionType::WINDOW_NTILE: {
|
|
61488
60303
|
D_ASSERT(payload_collection.ColumnCount() == 1);
|
|
61489
|
-
|
|
61490
|
-
|
|
61491
|
-
int64_t n_total = bounds.partition_end - bounds.partition_start;
|
|
61492
|
-
if (n_param > n_total) {
|
|
61493
|
-
// more groups allowed than we have values
|
|
61494
|
-
// map every entry to a unique group
|
|
61495
|
-
n_param = n_total;
|
|
61496
|
-
}
|
|
61497
|
-
int64_t n_size = (n_total / n_param);
|
|
61498
|
-
// find the row idx within the group
|
|
61499
|
-
D_ASSERT(row_idx >= bounds.partition_start);
|
|
61500
|
-
int64_t adjusted_row_idx = row_idx - bounds.partition_start;
|
|
61501
|
-
// now compute the ntile
|
|
61502
|
-
int64_t n_large = n_total - n_param * n_size;
|
|
61503
|
-
int64_t i_small = n_large * (n_size + 1);
|
|
61504
|
-
int64_t result_ntile;
|
|
61505
|
-
|
|
61506
|
-
D_ASSERT((n_large * (n_size + 1) + (n_param - n_large) * n_size) == n_total);
|
|
61507
|
-
|
|
61508
|
-
if (adjusted_row_idx < i_small) {
|
|
61509
|
-
result_ntile = 1 + adjusted_row_idx / (n_size + 1);
|
|
60304
|
+
if (CellIsNull(payload_collection, 0, row_idx)) {
|
|
60305
|
+
FlatVector::SetNull(result, output_offset, true);
|
|
61510
60306
|
} else {
|
|
61511
|
-
|
|
60307
|
+
auto n_param = GetCell<int64_t>(payload_collection, 0, row_idx);
|
|
60308
|
+
if (n_param < 1) {
|
|
60309
|
+
throw InvalidInputException("Argument for ntile must be greater than zero");
|
|
60310
|
+
}
|
|
60311
|
+
// With thanks from SQLite's ntileValueFunc()
|
|
60312
|
+
int64_t n_total = bounds.partition_end - bounds.partition_start;
|
|
60313
|
+
if (n_param > n_total) {
|
|
60314
|
+
// more groups allowed than we have values
|
|
60315
|
+
// map every entry to a unique group
|
|
60316
|
+
n_param = n_total;
|
|
60317
|
+
}
|
|
60318
|
+
int64_t n_size = (n_total / n_param);
|
|
60319
|
+
// find the row idx within the group
|
|
60320
|
+
D_ASSERT(row_idx >= bounds.partition_start);
|
|
60321
|
+
int64_t adjusted_row_idx = row_idx - bounds.partition_start;
|
|
60322
|
+
// now compute the ntile
|
|
60323
|
+
int64_t n_large = n_total - n_param * n_size;
|
|
60324
|
+
int64_t i_small = n_large * (n_size + 1);
|
|
60325
|
+
int64_t result_ntile;
|
|
60326
|
+
|
|
60327
|
+
D_ASSERT((n_large * (n_size + 1) + (n_param - n_large) * n_size) == n_total);
|
|
60328
|
+
|
|
60329
|
+
if (adjusted_row_idx < i_small) {
|
|
60330
|
+
result_ntile = 1 + adjusted_row_idx / (n_size + 1);
|
|
60331
|
+
} else {
|
|
60332
|
+
result_ntile = 1 + n_large + (adjusted_row_idx - i_small) / n_size;
|
|
60333
|
+
}
|
|
60334
|
+
// result has to be between [1, NTILE]
|
|
60335
|
+
D_ASSERT(result_ntile >= 1 && result_ntile <= n_param);
|
|
60336
|
+
auto rdata = FlatVector::GetData<int64_t>(result);
|
|
60337
|
+
rdata[output_offset] = result_ntile;
|
|
61512
60338
|
}
|
|
61513
|
-
// result has to be between [1, NTILE]
|
|
61514
|
-
D_ASSERT(result_ntile >= 1 && result_ntile <= n_param);
|
|
61515
|
-
auto rdata = FlatVector::GetData<int64_t>(result);
|
|
61516
|
-
rdata[output_offset] = result_ntile;
|
|
61517
60339
|
break;
|
|
61518
60340
|
}
|
|
61519
60341
|
case ExpressionType::WINDOW_LEAD:
|
|
@@ -107347,6 +106169,9 @@ struct BaseCSVData : public TableFunctionData {
|
|
|
107347
106169
|
vector<string> files;
|
|
107348
106170
|
//! The CSV reader options
|
|
107349
106171
|
BufferedCSVReaderOptions options;
|
|
106172
|
+
//! Offsets for generated columns
|
|
106173
|
+
idx_t filename_col_idx;
|
|
106174
|
+
idx_t hive_partition_col_idx;
|
|
107350
106175
|
|
|
107351
106176
|
void Finalize();
|
|
107352
106177
|
};
|
|
@@ -108543,6 +107368,7 @@ void BuiltinFunctions::RegisterTableFunctions() {
|
|
|
108543
107368
|
|
|
108544
107369
|
|
|
108545
107370
|
|
|
107371
|
+
|
|
108546
107372
|
#include <limits>
|
|
108547
107373
|
|
|
108548
107374
|
namespace duckdb {
|
|
@@ -108591,6 +107417,8 @@ static unique_ptr<FunctionData> ReadCSVBind(ClientContext &context, TableFunctio
|
|
|
108591
107417
|
options.normalize_names = BooleanValue::Get(kv.second);
|
|
108592
107418
|
} else if (loption == "filename") {
|
|
108593
107419
|
options.include_file_name = BooleanValue::Get(kv.second);
|
|
107420
|
+
} else if (loption == "hive_partitioning") {
|
|
107421
|
+
options.include_parsed_hive_partitions = BooleanValue::Get(kv.second);
|
|
108594
107422
|
} else {
|
|
108595
107423
|
options.SetReadOption(loption, kv.second, names);
|
|
108596
107424
|
}
|
|
@@ -108615,9 +107443,20 @@ static unique_ptr<FunctionData> ReadCSVBind(ClientContext &context, TableFunctio
|
|
|
108615
107443
|
D_ASSERT(return_types.size() == names.size());
|
|
108616
107444
|
}
|
|
108617
107445
|
if (result->options.include_file_name) {
|
|
107446
|
+
result->filename_col_idx = names.size();
|
|
108618
107447
|
return_types.emplace_back(LogicalType::VARCHAR);
|
|
108619
107448
|
names.emplace_back("filename");
|
|
108620
107449
|
}
|
|
107450
|
+
|
|
107451
|
+
if (result->options.include_parsed_hive_partitions) {
|
|
107452
|
+
auto partitions = ParseHivePartitions(result->files[0]);
|
|
107453
|
+
result->hive_partition_col_idx = names.size();
|
|
107454
|
+
for (auto &part : partitions) {
|
|
107455
|
+
return_types.emplace_back(LogicalType::VARCHAR);
|
|
107456
|
+
names.emplace_back(part.first);
|
|
107457
|
+
}
|
|
107458
|
+
}
|
|
107459
|
+
result->options.names = names;
|
|
108621
107460
|
return move(result);
|
|
108622
107461
|
}
|
|
108623
107462
|
|
|
@@ -108668,11 +107507,34 @@ static void ReadCSVFunction(ClientContext &context, TableFunctionInput &data_p,
|
|
|
108668
107507
|
break;
|
|
108669
107508
|
}
|
|
108670
107509
|
} while (true);
|
|
107510
|
+
|
|
108671
107511
|
if (bind_data.options.include_file_name) {
|
|
108672
|
-
auto &col = output.data.
|
|
107512
|
+
auto &col = output.data[bind_data.filename_col_idx];
|
|
108673
107513
|
col.SetValue(0, Value(data.csv_reader->options.file_path));
|
|
108674
107514
|
col.SetVectorType(VectorType::CONSTANT_VECTOR);
|
|
108675
107515
|
}
|
|
107516
|
+
if (bind_data.options.include_parsed_hive_partitions) {
|
|
107517
|
+
auto partitions = ParseHivePartitions(data.csv_reader->options.file_path);
|
|
107518
|
+
|
|
107519
|
+
idx_t i = bind_data.hive_partition_col_idx;
|
|
107520
|
+
|
|
107521
|
+
if (partitions.size() != (bind_data.options.names.size() - bind_data.hive_partition_col_idx)) {
|
|
107522
|
+
throw IOException("Hive partition count mismatch, expected " +
|
|
107523
|
+
std::to_string(bind_data.options.names.size() - bind_data.hive_partition_col_idx) +
|
|
107524
|
+
" hive partitions, got " + std::to_string(partitions.size()) + "\n");
|
|
107525
|
+
}
|
|
107526
|
+
|
|
107527
|
+
for (auto &part : partitions) {
|
|
107528
|
+
if (bind_data.options.names[i] != part.first) {
|
|
107529
|
+
throw IOException("Hive partition names mismatch, expected '" + bind_data.options.names[i] +
|
|
107530
|
+
"' but found '" + part.first + "' for file '" + data.csv_reader->options.file_path +
|
|
107531
|
+
"'");
|
|
107532
|
+
}
|
|
107533
|
+
auto &col = output.data[i++];
|
|
107534
|
+
col.SetValue(0, Value(part.second));
|
|
107535
|
+
col.SetVectorType(VectorType::CONSTANT_VECTOR);
|
|
107536
|
+
}
|
|
107537
|
+
}
|
|
108676
107538
|
}
|
|
108677
107539
|
|
|
108678
107540
|
static void ReadCSVAddNamedParameters(TableFunction &table_function) {
|
|
@@ -108693,6 +107555,7 @@ static void ReadCSVAddNamedParameters(TableFunction &table_function) {
|
|
|
108693
107555
|
table_function.named_parameters["normalize_names"] = LogicalType::BOOLEAN;
|
|
108694
107556
|
table_function.named_parameters["compression"] = LogicalType::VARCHAR;
|
|
108695
107557
|
table_function.named_parameters["filename"] = LogicalType::BOOLEAN;
|
|
107558
|
+
table_function.named_parameters["hive_partitioning"] = LogicalType::BOOLEAN;
|
|
108696
107559
|
table_function.named_parameters["skip"] = LogicalType::BIGINT;
|
|
108697
107560
|
table_function.named_parameters["max_line_size"] = LogicalType::VARCHAR;
|
|
108698
107561
|
table_function.named_parameters["maximum_line_size"] = LogicalType::VARCHAR;
|
|
@@ -140064,7 +138927,7 @@ unique_ptr<Expression> MoveConstantsRule::Apply(LogicalOperator &op, vector<Expr
|
|
|
140064
138927
|
|
|
140065
138928
|
|
|
140066
138929
|
// LICENSE_CHANGE_BEGIN
|
|
140067
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
138930
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
140068
138931
|
// See the end of this file for a list
|
|
140069
138932
|
|
|
140070
138933
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -140163,7 +139026,7 @@ unique_ptr<Expression> MoveConstantsRule::Apply(LogicalOperator &op, vector<Expr
|
|
|
140163
139026
|
|
|
140164
139027
|
|
|
140165
139028
|
// LICENSE_CHANGE_BEGIN
|
|
140166
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
139029
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
140167
139030
|
// See the end of this file for a list
|
|
140168
139031
|
|
|
140169
139032
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -140207,7 +139070,7 @@ unique_ptr<Expression> MoveConstantsRule::Apply(LogicalOperator &op, vector<Expr
|
|
|
140207
139070
|
|
|
140208
139071
|
|
|
140209
139072
|
// LICENSE_CHANGE_BEGIN
|
|
140210
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
139073
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
140211
139074
|
// See the end of this file for a list
|
|
140212
139075
|
|
|
140213
139076
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -140332,7 +139195,7 @@ class LogMessageFatal : public LogMessage {
|
|
|
140332
139195
|
|
|
140333
139196
|
|
|
140334
139197
|
// LICENSE_CHANGE_BEGIN
|
|
140335
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
139198
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
140336
139199
|
// See the end of this file for a list
|
|
140337
139200
|
|
|
140338
139201
|
/*
|
|
@@ -194771,7 +193634,7 @@ void UndoBuffer::Rollback() noexcept {
|
|
|
194771
193634
|
|
|
194772
193635
|
|
|
194773
193636
|
// LICENSE_CHANGE_BEGIN
|
|
194774
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
193637
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #2
|
|
194775
193638
|
// See the end of this file for a list
|
|
194776
193639
|
|
|
194777
193640
|
// Formatting library for C++
|
|
@@ -194784,7 +193647,7 @@ void UndoBuffer::Rollback() noexcept {
|
|
|
194784
193647
|
|
|
194785
193648
|
|
|
194786
193649
|
// LICENSE_CHANGE_BEGIN
|
|
194787
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
193650
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #2
|
|
194788
193651
|
// See the end of this file for a list
|
|
194789
193652
|
|
|
194790
193653
|
// Formatting library for C++ - implementation
|
|
@@ -196181,7 +195044,7 @@ FMT_END_NAMESPACE
|
|
|
196181
195044
|
|
|
196182
195045
|
|
|
196183
195046
|
// LICENSE_CHANGE_BEGIN
|
|
196184
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
195047
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #4
|
|
196185
195048
|
// See the end of this file for a list
|
|
196186
195049
|
|
|
196187
195050
|
/**************************************************************************
|
|
@@ -203733,7 +202596,7 @@ mz_bool mz_zip_end(mz_zip_archive *pZip)
|
|
|
203733
202596
|
|
|
203734
202597
|
|
|
203735
202598
|
// LICENSE_CHANGE_BEGIN
|
|
203736
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
202599
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
203737
202600
|
// See the end of this file for a list
|
|
203738
202601
|
|
|
203739
202602
|
// Copyright 2008 The RE2 Authors. All Rights Reserved.
|
|
@@ -203765,7 +202628,7 @@ mz_bool mz_zip_end(mz_zip_archive *pZip)
|
|
|
203765
202628
|
|
|
203766
202629
|
|
|
203767
202630
|
// LICENSE_CHANGE_BEGIN
|
|
203768
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
202631
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
203769
202632
|
// See the end of this file for a list
|
|
203770
202633
|
|
|
203771
202634
|
// Copyright 2018 The RE2 Authors. All Rights Reserved.
|
|
@@ -203830,7 +202693,7 @@ class PODArray {
|
|
|
203830
202693
|
|
|
203831
202694
|
|
|
203832
202695
|
// LICENSE_CHANGE_BEGIN
|
|
203833
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
202696
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
203834
202697
|
// See the end of this file for a list
|
|
203835
202698
|
|
|
203836
202699
|
// Copyright 2007 The RE2 Authors. All Rights Reserved.
|
|
@@ -203857,7 +202720,7 @@ class PODArray {
|
|
|
203857
202720
|
|
|
203858
202721
|
|
|
203859
202722
|
// LICENSE_CHANGE_BEGIN
|
|
203860
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
202723
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
203861
202724
|
// See the end of this file for a list
|
|
203862
202725
|
|
|
203863
202726
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -204259,7 +203122,7 @@ template<typename Value> bool SparseArray<Value>::less(const IndexValue& a,
|
|
|
204259
203122
|
|
|
204260
203123
|
|
|
204261
203124
|
// LICENSE_CHANGE_BEGIN
|
|
204262
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
203125
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
204263
203126
|
// See the end of this file for a list
|
|
204264
203127
|
|
|
204265
203128
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -205301,7 +204164,7 @@ bool Prog::SearchBitState(const StringPiece& text,
|
|
|
205301
204164
|
|
|
205302
204165
|
|
|
205303
204166
|
// LICENSE_CHANGE_BEGIN
|
|
205304
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
204167
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
205305
204168
|
// See the end of this file for a list
|
|
205306
204169
|
|
|
205307
204170
|
// Copyright 2007 The RE2 Authors. All Rights Reserved.
|
|
@@ -205328,7 +204191,7 @@ bool Prog::SearchBitState(const StringPiece& text,
|
|
|
205328
204191
|
|
|
205329
204192
|
|
|
205330
204193
|
// LICENSE_CHANGE_BEGIN
|
|
205331
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
204194
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
205332
204195
|
// See the end of this file for a list
|
|
205333
204196
|
|
|
205334
204197
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -206844,7 +205707,7 @@ Prog* Prog::CompileSet(Regexp* re, RE2::Anchor anchor, int64_t max_mem) {
|
|
|
206844
205707
|
|
|
206845
205708
|
|
|
206846
205709
|
// LICENSE_CHANGE_BEGIN
|
|
206847
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
205710
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
206848
205711
|
// See the end of this file for a list
|
|
206849
205712
|
|
|
206850
205713
|
// Copyright 2008 The RE2 Authors. All Rights Reserved.
|
|
@@ -206889,7 +205752,7 @@ Prog* Prog::CompileSet(Regexp* re, RE2::Anchor anchor, int64_t max_mem) {
|
|
|
206889
205752
|
|
|
206890
205753
|
|
|
206891
205754
|
// LICENSE_CHANGE_BEGIN
|
|
206892
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
205755
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
206893
205756
|
// See the end of this file for a list
|
|
206894
205757
|
|
|
206895
205758
|
// Copyright 2016 The RE2 Authors. All Rights Reserved.
|
|
@@ -206940,7 +205803,7 @@ class HashMix {
|
|
|
206940
205803
|
|
|
206941
205804
|
|
|
206942
205805
|
// LICENSE_CHANGE_BEGIN
|
|
206943
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
205806
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
206944
205807
|
// See the end of this file for a list
|
|
206945
205808
|
|
|
206946
205809
|
// Copyright 2007 The RE2 Authors. All Rights Reserved.
|
|
@@ -207084,7 +205947,7 @@ class WriterMutexLock {
|
|
|
207084
205947
|
|
|
207085
205948
|
|
|
207086
205949
|
// LICENSE_CHANGE_BEGIN
|
|
207087
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
205950
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
207088
205951
|
// See the end of this file for a list
|
|
207089
205952
|
|
|
207090
205953
|
// Copyright 2016 The RE2 Authors. All Rights Reserved.
|
|
@@ -209160,7 +208023,7 @@ bool Prog::PossibleMatchRange(std::string* min, std::string* max, int maxlen) {
|
|
|
209160
208023
|
|
|
209161
208024
|
|
|
209162
208025
|
// LICENSE_CHANGE_BEGIN
|
|
209163
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
208026
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
209164
208027
|
// See the end of this file for a list
|
|
209165
208028
|
|
|
209166
208029
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -209170,7 +208033,7 @@ bool Prog::PossibleMatchRange(std::string* min, std::string* max, int maxlen) {
|
|
|
209170
208033
|
|
|
209171
208034
|
|
|
209172
208035
|
// LICENSE_CHANGE_BEGIN
|
|
209173
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
208036
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
209174
208037
|
// See the end of this file for a list
|
|
209175
208038
|
|
|
209176
208039
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -209296,7 +208159,7 @@ class FilteredRE2 {
|
|
|
209296
208159
|
|
|
209297
208160
|
|
|
209298
208161
|
// LICENSE_CHANGE_BEGIN
|
|
209299
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
208162
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
209300
208163
|
// See the end of this file for a list
|
|
209301
208164
|
|
|
209302
208165
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -209414,7 +208277,7 @@ class Prefilter {
|
|
|
209414
208277
|
|
|
209415
208278
|
|
|
209416
208279
|
// LICENSE_CHANGE_BEGIN
|
|
209417
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
208280
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
209418
208281
|
// See the end of this file for a list
|
|
209419
208282
|
|
|
209420
208283
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -209674,7 +208537,7 @@ void FilteredRE2::PrintPrefilter(int regexpid) {
|
|
|
209674
208537
|
|
|
209675
208538
|
|
|
209676
208539
|
// LICENSE_CHANGE_BEGIN
|
|
209677
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
208540
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
209678
208541
|
// See the end of this file for a list
|
|
209679
208542
|
|
|
209680
208543
|
// Copyright 2008 The RE2 Authors. All Rights Reserved.
|
|
@@ -209870,7 +208733,7 @@ static bool CanBeEmptyString(Regexp* re) {
|
|
|
209870
208733
|
|
|
209871
208734
|
|
|
209872
208735
|
// LICENSE_CHANGE_BEGIN
|
|
209873
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
208736
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
209874
208737
|
// See the end of this file for a list
|
|
209875
208738
|
|
|
209876
208739
|
// Copyright 2006-2007 The RE2 Authors. All Rights Reserved.
|
|
@@ -210593,7 +209456,7 @@ void Prog::Fanout(SparseArray<int>* fanout) {
|
|
|
210593
209456
|
|
|
210594
209457
|
|
|
210595
209458
|
// LICENSE_CHANGE_BEGIN
|
|
210596
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
209459
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
210597
209460
|
// See the end of this file for a list
|
|
210598
209461
|
|
|
210599
209462
|
// Copyright 2008 The RE2 Authors. All Rights Reserved.
|
|
@@ -211177,7 +210040,7 @@ fail:
|
|
|
211177
210040
|
|
|
211178
210041
|
|
|
211179
210042
|
// LICENSE_CHANGE_BEGIN
|
|
211180
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
210043
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
211181
210044
|
// See the end of this file for a list
|
|
211182
210045
|
|
|
211183
210046
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -211217,7 +210080,7 @@ fail:
|
|
|
211217
210080
|
|
|
211218
210081
|
|
|
211219
210082
|
// LICENSE_CHANGE_BEGIN
|
|
211220
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
210083
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
211221
210084
|
// See the end of this file for a list
|
|
211222
210085
|
|
|
211223
210086
|
// Copyright 2008 The RE2 Authors. All Rights Reserved.
|
|
@@ -211305,7 +210168,7 @@ extern Rune ApplyFold(const CaseFold *f, Rune r);
|
|
|
211305
210168
|
|
|
211306
210169
|
|
|
211307
210170
|
// LICENSE_CHANGE_BEGIN
|
|
211308
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
210171
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
211309
210172
|
// See the end of this file for a list
|
|
211310
210173
|
|
|
211311
210174
|
// Copyright 2008 The RE2 Authors. All Rights Reserved.
|
|
@@ -213813,7 +212676,7 @@ Regexp* Regexp::Parse(const StringPiece& s, ParseFlags global_flags,
|
|
|
213813
212676
|
|
|
213814
212677
|
|
|
213815
212678
|
// LICENSE_CHANGE_BEGIN
|
|
213816
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
212679
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
213817
212680
|
// See the end of this file for a list
|
|
213818
212681
|
|
|
213819
212682
|
// GENERATED BY make_perl_groups.pl; DO NOT EDIT.
|
|
@@ -213941,7 +212804,7 @@ const int num_posix_groups = 28;
|
|
|
213941
212804
|
|
|
213942
212805
|
|
|
213943
212806
|
// LICENSE_CHANGE_BEGIN
|
|
213944
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
212807
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
213945
212808
|
// See the end of this file for a list
|
|
213946
212809
|
|
|
213947
212810
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -214642,7 +213505,7 @@ Prefilter* Prefilter::FromRE2(const RE2* re2) {
|
|
|
214642
213505
|
|
|
214643
213506
|
|
|
214644
213507
|
// LICENSE_CHANGE_BEGIN
|
|
214645
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
213508
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
214646
213509
|
// See the end of this file for a list
|
|
214647
213510
|
|
|
214648
213511
|
// Copyright 2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -215053,7 +213916,7 @@ std::string PrefilterTree::DebugNodeString(Prefilter* node) const {
|
|
|
215053
213916
|
|
|
215054
213917
|
|
|
215055
213918
|
// LICENSE_CHANGE_BEGIN
|
|
215056
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
213919
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
215057
213920
|
// See the end of this file for a list
|
|
215058
213921
|
|
|
215059
213922
|
// Copyright 2007 The RE2 Authors. All Rights Reserved.
|
|
@@ -215077,7 +213940,7 @@ std::string PrefilterTree::DebugNodeString(Prefilter* node) const {
|
|
|
215077
213940
|
|
|
215078
213941
|
|
|
215079
213942
|
// LICENSE_CHANGE_BEGIN
|
|
215080
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
213943
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
215081
213944
|
// See the end of this file for a list
|
|
215082
213945
|
|
|
215083
213946
|
// Copyright 2016 The RE2 Authors. All Rights Reserved.
|
|
@@ -216103,7 +214966,7 @@ void Prog::ComputeHints(std::vector<Inst>* flat, int begin, int end) {
|
|
|
216103
214966
|
|
|
216104
214967
|
|
|
216105
214968
|
// LICENSE_CHANGE_BEGIN
|
|
216106
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
214969
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
216107
214970
|
// See the end of this file for a list
|
|
216108
214971
|
|
|
216109
214972
|
// Copyright 2003-2009 The RE2 Authors. All Rights Reserved.
|
|
@@ -217347,7 +216210,7 @@ DEFINE_INTEGER_PARSER(ulonglong)
|
|
|
217347
216210
|
|
|
217348
216211
|
|
|
217349
216212
|
// LICENSE_CHANGE_BEGIN
|
|
217350
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
216213
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
217351
216214
|
// See the end of this file for a list
|
|
217352
216215
|
|
|
217353
216216
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -218327,7 +217190,7 @@ CharClass* CharClassBuilder::GetCharClass() {
|
|
|
218327
217190
|
|
|
218328
217191
|
|
|
218329
217192
|
// LICENSE_CHANGE_BEGIN
|
|
218330
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
217193
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
218331
217194
|
// See the end of this file for a list
|
|
218332
217195
|
|
|
218333
217196
|
// Copyright 2010 The RE2 Authors. All Rights Reserved.
|
|
@@ -218337,7 +217200,7 @@ CharClass* CharClassBuilder::GetCharClass() {
|
|
|
218337
217200
|
|
|
218338
217201
|
|
|
218339
217202
|
// LICENSE_CHANGE_BEGIN
|
|
218340
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
217203
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
218341
217204
|
// See the end of this file for a list
|
|
218342
217205
|
|
|
218343
217206
|
// Copyright 2010 The RE2 Authors. All Rights Reserved.
|
|
@@ -218578,7 +217441,7 @@ bool RE2::Set::Match(const StringPiece& text, std::vector<int>* v,
|
|
|
218578
217441
|
|
|
218579
217442
|
|
|
218580
217443
|
// LICENSE_CHANGE_BEGIN
|
|
218581
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
217444
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
218582
217445
|
// See the end of this file for a list
|
|
218583
217446
|
|
|
218584
217447
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -219243,7 +218106,7 @@ Regexp* SimplifyWalker::SimplifyCharClass(Regexp* re) {
|
|
|
219243
218106
|
|
|
219244
218107
|
|
|
219245
218108
|
// LICENSE_CHANGE_BEGIN
|
|
219246
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
218109
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
219247
218110
|
// See the end of this file for a list
|
|
219248
218111
|
|
|
219249
218112
|
// Copyright 2004 The RE2 Authors. All Rights Reserved.
|
|
@@ -219317,7 +218180,7 @@ std::ostream& operator<<(std::ostream& o, const StringPiece& p) {
|
|
|
219317
218180
|
|
|
219318
218181
|
|
|
219319
218182
|
// LICENSE_CHANGE_BEGIN
|
|
219320
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
218183
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
219321
218184
|
// See the end of this file for a list
|
|
219322
218185
|
|
|
219323
218186
|
// Copyright 2006 The RE2 Authors. All Rights Reserved.
|
|
@@ -219675,7 +218538,7 @@ static void AppendCCRange(std::string* t, Rune lo, Rune hi) {
|
|
|
219675
218538
|
|
|
219676
218539
|
|
|
219677
218540
|
// LICENSE_CHANGE_BEGIN
|
|
219678
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
218541
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
219679
218542
|
// See the end of this file for a list
|
|
219680
218543
|
|
|
219681
218544
|
|
|
@@ -220251,7 +219114,7 @@ const int num_unicode_tolower = 194;
|
|
|
220251
219114
|
|
|
220252
219115
|
|
|
220253
219116
|
// LICENSE_CHANGE_BEGIN
|
|
220254
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
219117
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
220255
219118
|
// See the end of this file for a list
|
|
220256
219119
|
|
|
220257
219120
|
|
|
@@ -226319,7 +225182,7 @@ const int num_unicode_groups = 184;
|
|
|
226319
225182
|
|
|
226320
225183
|
|
|
226321
225184
|
// LICENSE_CHANGE_BEGIN
|
|
226322
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
225185
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
226323
225186
|
// See the end of this file for a list
|
|
226324
225187
|
|
|
226325
225188
|
/*
|
|
@@ -226588,7 +225451,7 @@ utfrune(const char *s, Rune c)
|
|
|
226588
225451
|
|
|
226589
225452
|
|
|
226590
225453
|
// LICENSE_CHANGE_BEGIN
|
|
226591
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
225454
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #1
|
|
226592
225455
|
// See the end of this file for a list
|
|
226593
225456
|
|
|
226594
225457
|
// Copyright 1999-2005 The RE2 Authors. All Rights Reserved.
|
|
@@ -230765,7 +229628,7 @@ void __fastpack64(const uint64_t *__restrict in, uint32_t *__restrict out) {
|
|
|
230765
229628
|
|
|
230766
229629
|
|
|
230767
229630
|
// LICENSE_CHANGE_BEGIN
|
|
230768
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
229631
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #3
|
|
230769
229632
|
// See the end of this file for a list
|
|
230770
229633
|
|
|
230771
229634
|
/* -*- mode: c; c-basic-offset: 2; tab-width: 2; indent-tabs-mode: nil -*- */
|
|
@@ -230825,7 +229688,7 @@ namespace duckdb {
|
|
|
230825
229688
|
|
|
230826
229689
|
|
|
230827
229690
|
// LICENSE_CHANGE_BEGIN
|
|
230828
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
229691
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #3
|
|
230829
229692
|
// See the end of this file for a list
|
|
230830
229693
|
|
|
230831
229694
|
static const utf8proc_uint16_t utf8proc_sequences[] = {
|
|
@@ -246479,7 +245342,7 @@ UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC_Casefold(const utf8proc_uint8
|
|
|
246479
245342
|
|
|
246480
245343
|
|
|
246481
245344
|
// LICENSE_CHANGE_BEGIN
|
|
246482
|
-
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #
|
|
245345
|
+
// The following code up to LICENSE_CHANGE_END is subject to THIRD PARTY LICENSE #3
|
|
246483
245346
|
// See the end of this file for a list
|
|
246484
245347
|
|
|
246485
245348
|
|
|
@@ -308599,6 +307462,38 @@ bool MbedTlsWrapper::IsValidSha256Signature(const std::string &pubkey, const std
|
|
|
308599
307462
|
|
|
308600
307463
|
### THIRD PARTY LICENSE #1 ###
|
|
308601
307464
|
|
|
307465
|
+
// Copyright (c) 2009 The RE2 Authors. All rights reserved.
|
|
307466
|
+
//
|
|
307467
|
+
// Redistribution and use in source and binary forms, with or without
|
|
307468
|
+
// modification, are permitted provided that the following conditions are
|
|
307469
|
+
// met:
|
|
307470
|
+
//
|
|
307471
|
+
// * Redistributions of source code must retain the above copyright
|
|
307472
|
+
// notice, this list of conditions and the following disclaimer.
|
|
307473
|
+
// * Redistributions in binary form must reproduce the above
|
|
307474
|
+
// copyright notice, this list of conditions and the following disclaimer
|
|
307475
|
+
// in the documentation and/or other materials provided with the
|
|
307476
|
+
// distribution.
|
|
307477
|
+
// * Neither the name of Google Inc. nor the names of its
|
|
307478
|
+
// contributors may be used to endorse or promote products derived from
|
|
307479
|
+
// this software without specific prior written permission.
|
|
307480
|
+
//
|
|
307481
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
307482
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
307483
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
307484
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
307485
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
307486
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
307487
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
307488
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
307489
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
307490
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
307491
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
307492
|
+
|
|
307493
|
+
|
|
307494
|
+
|
|
307495
|
+
### THIRD PARTY LICENSE #2 ###
|
|
307496
|
+
|
|
308602
307497
|
Copyright (c) 2012 - present, Victor Zverovich
|
|
308603
307498
|
|
|
308604
307499
|
Permission is hereby granted, free of charge, to any person obtaining
|
|
@@ -308629,7 +307524,7 @@ without including the above copyright and permission notices.
|
|
|
308629
307524
|
|
|
308630
307525
|
|
|
308631
307526
|
|
|
308632
|
-
### THIRD PARTY LICENSE #
|
|
307527
|
+
### THIRD PARTY LICENSE #3 ###
|
|
308633
307528
|
|
|
308634
307529
|
## utf8proc license ##
|
|
308635
307530
|
|
|
@@ -308727,7 +307622,7 @@ trademarks mentioned herein are the property of their respective owners.
|
|
|
308727
307622
|
|
|
308728
307623
|
|
|
308729
307624
|
|
|
308730
|
-
### THIRD PARTY LICENSE #
|
|
307625
|
+
### THIRD PARTY LICENSE #4 ###
|
|
308731
307626
|
|
|
308732
307627
|
Copyright 2013-2014 RAD Game Tools and Valve Software
|
|
308733
307628
|
Copyright 2010-2014 Rich Geldreich and Tenacious Software LLC
|
|
@@ -308754,7 +307649,7 @@ THE SOFTWARE.
|
|
|
308754
307649
|
|
|
308755
307650
|
|
|
308756
307651
|
|
|
308757
|
-
### THIRD PARTY LICENSE #
|
|
307652
|
+
### THIRD PARTY LICENSE #5 ###
|
|
308758
307653
|
|
|
308759
307654
|
Permission is hereby granted, free of charge, to any
|
|
308760
307655
|
person obtaining a copy of this software and associated
|
|
@@ -308782,7 +307677,7 @@ DEALINGS IN THE SOFTWARE.
|
|
|
308782
307677
|
|
|
308783
307678
|
|
|
308784
307679
|
|
|
308785
|
-
### THIRD PARTY LICENSE #
|
|
307680
|
+
### THIRD PARTY LICENSE #6 ###
|
|
308786
307681
|
|
|
308787
307682
|
Copyright (c) 2014-2017 Melissa O'Neill and PCG Project contributors
|
|
308788
307683
|
|
|
@@ -308805,38 +307700,6 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
|
308805
307700
|
SOFTWARE.
|
|
308806
307701
|
|
|
308807
307702
|
|
|
308808
|
-
### THIRD PARTY LICENSE #6 ###
|
|
308809
|
-
|
|
308810
|
-
// Copyright (c) 2009 The RE2 Authors. All rights reserved.
|
|
308811
|
-
//
|
|
308812
|
-
// Redistribution and use in source and binary forms, with or without
|
|
308813
|
-
// modification, are permitted provided that the following conditions are
|
|
308814
|
-
// met:
|
|
308815
|
-
//
|
|
308816
|
-
// * Redistributions of source code must retain the above copyright
|
|
308817
|
-
// notice, this list of conditions and the following disclaimer.
|
|
308818
|
-
// * Redistributions in binary form must reproduce the above
|
|
308819
|
-
// copyright notice, this list of conditions and the following disclaimer
|
|
308820
|
-
// in the documentation and/or other materials provided with the
|
|
308821
|
-
// distribution.
|
|
308822
|
-
// * Neither the name of Google Inc. nor the names of its
|
|
308823
|
-
// contributors may be used to endorse or promote products derived from
|
|
308824
|
-
// this software without specific prior written permission.
|
|
308825
|
-
//
|
|
308826
|
-
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
308827
|
-
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
308828
|
-
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
308829
|
-
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
308830
|
-
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
308831
|
-
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
308832
|
-
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
308833
|
-
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
308834
|
-
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
308835
|
-
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
308836
|
-
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
308837
|
-
|
|
308838
|
-
|
|
308839
|
-
|
|
308840
307703
|
### THIRD PARTY LICENSE #7 ###
|
|
308841
307704
|
|
|
308842
307705
|
Copyright (c) 2012 Art.sy, Inc.
|