Fixed build on systems with libc6

.travis.yml

@@ -2,6 +2,8 @@ language: c++
 sudo: false
 compiler:
     - gcc
+before_install:
+  - sudo apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 762E3157
 install:
     - export CXX="g++-4.8" CC="gcc-4.8"
 addons:

src/FactExtract/Parser/afglrparserlib/regexp.cpp

@@ -43,6 +43,7 @@ TRegexMatcher::TRegexMatcher(const TWtringBuf& pattern) {
     }
 
     NPire::TLexer lexer(final.begin(), final.end());
+    lexer.AddFeature(NPire::NFeatures::EnableUnicodeSequences());
     lexer.SetEncoding(NPire::NEncodings::Utf8());
     NPire::TFsm fsm = lexer.Parse();
     if (surround)
@@ -58,6 +59,7 @@ TRegexMatcher::~TRegexMatcher() {
 bool TRegexMatcher::IsCompatible(const TWtringBuf& pattern) {
     try {
         NPire::TLexer lexer(pattern.begin(), pattern.end());
+        lexer.AddFeature(NPire::NFeatures::EnableUnicodeSequences());
         lexer.Parse();
         return true;
     } catch (...) {

src/contrib/libs/pire/pire/extra.h

@@ -29,5 +29,6 @@
 #include <contrib/libs/pire/pire/extra/capture.h>
 #include <contrib/libs/pire/pire/extra/count.h>
 #include <contrib/libs/pire/pire/extra/glyphs.h>
+#include <contrib/libs/pire/pire/extra/unicode_support.h>
 
 #endif

src/contrib/libs/pire/pire/extra/unicode_support.cpp

@@ -0,0 +1,125 @@
+/*
+ * unicode_support.cpp -- implementation for the EnableUnicodeSequences feature.
+ *
+ * Copyright (c) 2018 YANDEX LLC
+ * Author: Andrey Logvin <[email protected]>
+ *
+ * This file is part of Pire, the Perl Incompatible
+ * Regular Expressions library.
+ *
+ * Pire is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Pire is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser Public License for more details.
+ * You should have received a copy of the GNU Lesser Public License
+ * along with Pire.  If not, see <http://www.gnu.org/licenses>.
+ */
+
+
+#include "unicode_support.h"
+
+#include <contrib/libs/pire/pire/re_lexer.h>
+//#include <util/stream/output.h>
+
+namespace Pire {
+
+namespace {
+    bool IsHexDigit(wchar32 ch) {
+        return ch < 256 && std::isxdigit(ch) != 0;
+    }
+
+    static const long hextable[] = {
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1, 0,1,2,3,4,5,6,7,8,9,-1,-1,-1,-1,-1,-1,-1,10,11,12,13,14,15,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
+            -1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1
+    };
+
+    class EnableUnicodeSequencesImpl : public Feature {
+    public:
+        bool Accepts(wchar32 c) const {
+            return c == (Control | 'x');
+        }
+
+        Term Lex() {
+            ystring hexStr;
+            GetChar();
+            wchar32 ch = PeekChar();
+            if (ch == '{') {
+                GetChar();
+                hexStr = ReadHexDigit([](wchar32 ch, size_t numAdded) -> bool {return ch == End || (numAdded != 0 && ch == '}');});
+                ch = GetChar();
+                if (ch != '}') {
+                    Error("Pire::EnableUnicodeSequencesImpl::Lex(): \"\\x{...\" sequence should be closed by \"}\"");
+                }
+            } else {
+                hexStr = ReadHexDigit([](wchar32, size_t numAdded) -> bool {return numAdded == 2;});
+                if (hexStr.size() != 2) {
+                    Error("Pire::EnableUnicodeSequencesImpl::Lex(): \"\\x...\" sequence should contain two symbols");
+                }
+            }
+            return Term::Character(HexToDec(hexStr));
+        }
+
+    private:
+        const wchar32 MAX_UNICODE = 0x10FFFF;
+
+//        ystring ReadHexDigit(std::function<bool(wchar32, size_t)> shouldStop) {
+        template<typename Lambda>
+        ystring ReadHexDigit(Lambda shouldStop) {
+            ystring result;
+            wchar32 ch = GetChar();
+            while (!shouldStop(ch, result.size())) {
+                if (!IsHexDigit(ch)) {
+                    Error("Pire::EnableUnicodeSequencesImpl::Lex(): \"\\x...\" sequence contains non-valid hex number");
+                }
+                result.push_back(ch);
+                ch = GetChar();
+            }
+            UngetChar(ch);
+            return result;
+        }
+
+        wchar32 HexToDec(const ystring& hexStr) {
+            wchar32 converted;
+            try {
+                // The above code is replacement for this
+                // converted = std::stoul(hexStr, 0, 16);
+
+                // StdOutStream() << hexStr << Endl;
+                converted = 0;
+                for (auto it = hexStr.begin(); it != hexStr.end(); ++it) {
+                    converted = (converted << 4) | hextable[*it];
+                }
+
+                if (converted > MAX_UNICODE) {
+                    throw std::out_of_range("stoul");
+                }
+
+            } catch (std::out_of_range&) {
+                converted = MAX_UNICODE + 1;
+            }
+            if (converted > MAX_UNICODE) {
+                Error("Pire::EnableUnicodeSequencesImpl::Lex(): hex number in \"\\x...\" sequence is too large");
+            }
+            return converted;
+        }
+    };
+}
+
+namespace Features {
+    Feature* EnableUnicodeSequences() { return new EnableUnicodeSequencesImpl; }
+};
+}

src/contrib/libs/pire/pire/extra/unicode_support.h

@@ -0,0 +1,42 @@
+/*
+ * unicode_support.h -- declaration of the EnableUnicodeSequences feature.
+ *
+ * Copyright (c) 2018 YANDEX LLC
+ * Author: Andrey Logvin <[email protected]>
+ *
+ * This file is part of Pire, the Perl Incompatible
+ * Regular Expressions library.
+ *
+ * Pire is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Pire is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser Public License for more details.
+ * You should have received a copy of the GNU Lesser Public License
+ * along with Pire.  If not, see <http://www.gnu.org/licenses>.
+ */
+
+
+#ifndef PIRE_EXTRA_SUPPORT_UNICODE_H
+#define PIRE_EXTRA_SUPPORT_UNICODE_H
+
+#include <memory>
+
+namespace Pire {
+class Feature;
+namespace Features {
+
+   /**
+    * A feature which tells Pire to convert \x{...} and \x... sequences
+    * to accordingly UTF-32 symbols
+    * e.g. \x00 == '\0', \x41 == A
+    */
+    Feature* EnableUnicodeSequences();
+}
+}
+
+#endif

src/contrib/tools/bison/gnulib/src/fflush.c

@@ -33,7 +33,7 @@
 #undef fflush
 
 
-#if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+#if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
 
 /* Clear the stream's ungetc buffer, preserving the value of ftello (fp).  */
 static void
@@ -71,7 +71,7 @@ clear_ungetc_buffer (FILE *fp)
 
 #endif
 
-#if ! (defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */)
+#if ! (defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */)
 
 # if (defined __sferror || defined __DragonFly__) && defined __SNPT /* FreeBSD, NetBSD, OpenBSD, DragonFly, Mac OS X, Cygwin */
 
@@ -145,7 +145,7 @@ rpl_fflush (FILE *stream)
   if (stream == NULL || ! freading (stream))
     return fflush (stream);
 
-#if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+#if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
 
   clear_ungetc_buffer_preserving_position (stream);
 

src/contrib/tools/bison/gnulib/src/fpurge.c

@@ -61,7 +61,7 @@ fpurge (FILE *fp)
   /* Most systems provide FILE as a struct and the necessary bitmask in
      <stdio.h>, because they need it for implementing getc() and putc() as
      fast macros.  */
-# if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+# if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
   fp->_IO_read_end = fp->_IO_read_ptr;
   fp->_IO_write_ptr = fp->_IO_write_base;
   /* Avoid memory leak when there is an active ungetc buffer.  */

src/contrib/tools/bison/gnulib/src/freadahead.c

@@ -25,7 +25,7 @@
 size_t
 freadahead (FILE *fp)
 {
-#if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+#if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
   if (fp->_IO_write_ptr > fp->_IO_write_base)
     return 0;
   return (fp->_IO_read_end - fp->_IO_read_ptr)

src/contrib/tools/bison/gnulib/src/freading.c

@@ -31,7 +31,7 @@ freading (FILE *fp)
   /* Most systems provide FILE as a struct and the necessary bitmask in
      <stdio.h>, because they need it for implementing getc() and putc() as
      fast macros.  */
-# if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+# if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
   return ((fp->_flags & _IO_NO_WRITES) != 0
           || ((fp->_flags & (_IO_NO_READS | _IO_CURRENTLY_PUTTING)) == 0
               && fp->_IO_read_base != NULL));

src/contrib/tools/bison/gnulib/src/fseeko.c

@@ -47,7 +47,7 @@ fseeko (FILE *fp, off_t offset, int whence)
 #endif
 
   /* These tests are based on fpurge.c.  */
-#if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+#if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
   if (fp->_IO_read_end == fp->_IO_read_ptr
       && fp->_IO_write_ptr == fp->_IO_write_base
       && fp->_IO_save_base == NULL)
@@ -121,7 +121,7 @@ fseeko (FILE *fp, off_t offset, int whence)
           return -1;
         }
 
-#if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+#if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
       fp->_flags &= ~_IO_EOF_SEEN;
       fp->_offset = pos;
 #elif defined __sferror || defined __DragonFly__ /* FreeBSD, NetBSD, OpenBSD, DragonFly, Mac OS X, Cygwin */

src/contrib/tools/bison/gnulib/src/fseterr.c

@@ -29,7 +29,7 @@ fseterr (FILE *fp)
   /* Most systems provide FILE as a struct and the necessary bitmask in
      <stdio.h>, because they need it for implementing getc() and putc() as
      fast macros.  */
-#if defined _IO_ftrylockfile || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5 */
+#if defined _IO_ftrylockfile || defined _IO_EOF_SEEN || __GNU_LIBRARY__ == 1 /* GNU libc, BeOS, Haiku, Linux libc5, Linux libc6 */
   fp->_flags |= _IO_ERR_SEEN;
 #elif defined __sferror || defined __DragonFly__ /* FreeBSD, NetBSD, OpenBSD, DragonFly, Mac OS X, Cygwin */
   fp_->_flags |= __SERR;

src/contrib/tools/bison/gnulib/src/stdio-impl.h

@@ -19,6 +19,13 @@
    have different naming conventions, or their access requires some casts.  */
 
 
+/* Glibc 2.28 made _IO_IN_BACKUP private.  For now, work around this
+   problem by defining it ourselves.  FIXME: Do not rely on glibc
+   internals.  */
+#if !defined _IO_IN_BACKUP && defined _IO_EOF_SEEN
+# define _IO_IN_BACKUP 0x100
+#endif
+
 /* BSD stdio derived implementations.  */
 
 #if defined __NetBSD__                         /* NetBSD */

src/library/pire/CMakeLists.txt

@@ -15,6 +15,7 @@ SRCS(
     extra/capture.cpp
     extra/count.cpp
     extra/glyphs.cpp
+    extra/unicode_support.cpp
     re_lexer.cpp
     re_parser.y
     extraencodings.cpp

src/library/pire/pire.h

@@ -46,6 +46,7 @@ namespace NPire {
         using Pire::Features::GlueSimilarGlyphs;
         using Pire::Features::AndNotSupport;
         using Pire::Features::Capture;
+        using Pire::Features::EnableUnicodeSequences;
     }
 
     namespace NEncodings {