Merge branch 'pan/update_pcre_8.33'

* pan/update_pcre_8.33:
  Workaround TR gnu/181328, GCC 4.2.1 20070831 on FreeBSD 9.1
  Clarify relation between erts_iolist_{size|to_buf}
  Fix backslash in titles of manpages
  Correct UTF-8 in stdlib's notes.xml
  Add more tests for corner error cases in erl_bif_re.c
  Add documentation of report_errors and match_limit(_recursion)
  Add match_limit and match_limit_recursion options
  Add return_errors option to re:run/3
  Add README for updating PCRE
  Add documentation of extensions to re module
  Add new options to Erlang re interface and mend dupnames
  Update PCRE doc part of re.xml to PCRE 8.33 state
  Integrate new PCRE test suites
  Integrate patch for PCRE bug id 1370
  Handle CRLF correctly in global regexp
  Add erts_prefix to pcre_library and update erl_bif_re
  Update to PCRE 8.33, w/o the erts_ prefix added

OTP-11204
OTP-11205
OTP-10285

1 files changed, 82 insertions, 36 deletions

diff --git a/erts/emulator/pcre/pcre_newline.c b/erts/emulator/pcre/pcre_newline.c
index 7dbda88aff..02394078d5 100644
--- a/erts/emulator/pcre/pcre_newline.c
+++ b/erts/emulator/pcre/pcre_newline.c
@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2008 University of Cambridge
+           Copyright (c) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -68,23 +68,33 @@ Arguments:
   type         the newline type
   endptr       pointer to the end of the string
   lenptr       where to return the length
-  utf8         TRUE if in utf8 mode
+  utf          TRUE if in utf mode
 
 Returns:       TRUE or FALSE
 */
 
 BOOL
-_erts_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr,
-  int *lenptr, BOOL utf8)
+PRIV(is_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR endptr, int *lenptr,
+  BOOL utf)
 {
-int c;
-if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
+pcre_uint32 c;
+(void)utf;
+#ifdef SUPPORT_UTF
+if (utf)
+  {
+  GETCHAR(c, ptr);
+  }
+else
+#endif  /* SUPPORT_UTF */
+  c = *ptr;
+
+/* Note that this function is called only for ANY or ANYCRLF. */
 
 if (type == NLTYPE_ANYCRLF) switch(c)
   {
-  case 0x000a: *lenptr = 1; return TRUE;             /* LF */
-  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
-               return TRUE;                          /* CR */
+  case CHAR_LF: *lenptr = 1; return TRUE;
+  case CHAR_CR: *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
+               return TRUE;
   default: return FALSE;
   }
 
@@ -92,14 +102,29 @@ if (type == NLTYPE_ANYCRLF) switch(c)
 
 else switch(c)
   {
-  case 0x000a:                                       /* LF */
-  case 0x000b:                                       /* VT */
-  case 0x000c: *lenptr = 1; return TRUE;             /* FF */
-  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
-               return TRUE;                          /* CR */
-  case 0x0085: *lenptr = utf8? 2 : 1; return TRUE;   /* NEL */
+#ifdef EBCDIC
+  case CHAR_NEL:
+#endif
+  case CHAR_LF:
+  case CHAR_VT:
+  case CHAR_FF: *lenptr = 1; return TRUE;
+
+  case CHAR_CR:
+  *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
+  return TRUE;
+
+#ifndef EBCDIC
+#ifdef COMPILE_PCRE8
+  case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE;
   case 0x2028:                                       /* LS */
   case 0x2029: *lenptr = 3; return TRUE;             /* PS */
+#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */
+  case CHAR_NEL:
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 1; return TRUE;             /* PS */
+#endif  /* COMPILE_PCRE8 */
+#endif  /* Not EBCDIC */
+
   default: return FALSE;
   }
 }
@@ -118,46 +143,67 @@ Arguments:
   type         the newline type
   startptr     pointer to the start of the string
   lenptr       where to return the length
-  utf8         TRUE if in utf8 mode
+  utf          TRUE if in utf mode
 
 Returns:       TRUE or FALSE
 */
 
 BOOL
-_erts_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr,
-  int *lenptr, BOOL utf8)
+PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr,
+  BOOL utf)
 {
-int c;
+pcre_uint32 c;
+(void)utf;
 ptr--;
-#ifdef SUPPORT_UTF8
-if (utf8)
+#ifdef SUPPORT_UTF
+if (utf)
   {
   BACKCHAR(ptr);
   GETCHAR(c, ptr);
   }
-else c = *ptr;
-#else   /* no UTF-8 support */
-c = *ptr;
-#endif  /* SUPPORT_UTF8 */
+else
+#endif  /* SUPPORT_UTF */
+  c = *ptr;
+
+/* Note that this function is called only for ANY or ANYCRLF. */
 
 if (type == NLTYPE_ANYCRLF) switch(c)
   {
-  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
-               return TRUE;                         /* LF */
-  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
+  case CHAR_LF:
+  *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
+  return TRUE;
+
+  case CHAR_CR: *lenptr = 1; return TRUE;
   default: return FALSE;
   }
 
+/* NLTYPE_ANY */
+
 else switch(c)
   {
-  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
-               return TRUE;                         /* LF */
-  case 0x000b:                                      /* VT */
-  case 0x000c:                                      /* FF */
-  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
-  case 0x0085: *lenptr = utf8? 2 : 1; return TRUE;  /* NEL */
-  case 0x2028:                                      /* LS */
-  case 0x2029: *lenptr = 3; return TRUE;            /* PS */
+  case CHAR_LF:
+  *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
+  return TRUE;
+
+#ifdef EBCDIC
+  case CHAR_NEL:
+#endif
+  case CHAR_VT:
+  case CHAR_FF:
+  case CHAR_CR: *lenptr = 1; return TRUE;
+
+#ifndef EBCDIC
+#ifdef COMPILE_PCRE8
+  case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE;
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 3; return TRUE;             /* PS */
+#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */
+  case CHAR_NEL:
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 1; return TRUE;             /* PS */
+#endif  /* COMPILE_PCRE8 */
+#endif  /* NotEBCDIC */
+
   default: return FALSE;
   }
 }