@port-labs/jq-node-bindings 0.0.14 → 0.0.15-dev1

package/deps/jq/modules/oniguruma/src/utf8.c

@@ -2,7 +2,7 @@
   utf8.c -  Oniguruma (regular expression library)
 **********************************************************************/
 /*-
- * Copyright (c) 2002-2016  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
+ * Copyright (c) 2002-2019  K.Kosako
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -29,7 +29,10 @@
 
 #include "regenc.h"
 
-//#define USE_INVALID_CODE_SCHEME
+/* U+0000 - U+10FFFF */
+#define USE_RFC3629_RANGE
+
+/* #define USE_INVALID_CODE_SCHEME */
 
 #ifdef USE_INVALID_CODE_SCHEME
 /* virtual codepoint values for invalid encoding byte 0xfe and 0xff */
@@ -57,7 +60,11 @@ static const int EncLen_UTF8[] = {
   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
   3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
+#ifdef USE_RFC3629_RANGE
+  4, 4, 4, 4, 4, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
+#else
   4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 1, 1
+#endif
 };
 
 static int
@@ -78,11 +85,11 @@ is_valid_mbc_string(const UChar* p, const UChar* end)
     len = mbc_enc_len(p++);
     if (len > 1) {
       for (i = 1; i < len; i++) {
-	if (p == end)
-	  return FALSE;
+        if (p == end)
+          return FALSE;
 
-	if (! utf8_istail(*p++))
-	  return FALSE;
+        if (! utf8_istail(*p++))
+          return FALSE;
       }
     }
   }
@@ -90,31 +97,6 @@ is_valid_mbc_string(const UChar* p, const UChar* end)
   return TRUE;
 }
 
-static int
-is_mbc_newline(const UChar* p, const UChar* end)
-{
-  if (p < end) {
-    if (*p == 0x0a) return 1;
-
-#ifdef USE_UNICODE_ALL_LINE_TERMINATORS
-#ifndef USE_CRNL_AS_LINE_TERMINATOR
-    if (*p == 0x0d) return 1;
-#endif
-    if (p + 1 < end) {
-      if (*(p+1) == 0x85 && *p == 0xc2) /* U+0085 */
-        return 1;
-      if (p + 2 < end) {
-        if ((*(p+2) == 0xa8 || *(p+2) == 0xa9)
-            && *(p+1) == 0x80 && *p == 0xe2)  /* U+2028, U+2029 */
-          return 1;
-      }
-    }
-#endif
-  }
-
-  return 0;
-}
-
 static OnigCodePoint
 mbc_to_code(const UChar* p, const UChar* end)
 {
@@ -122,7 +104,7 @@ mbc_to_code(const UChar* p, const UChar* end)
   OnigCodePoint n;
 
   len = mbc_enc_len(p);
-  if (len > end - p) len = end - p;
+  if (len > (int )(end - p)) len = (int )(end - p);
 
   c = *p++;
   if (len > 1) {
@@ -151,8 +133,10 @@ code_to_mbclen(OnigCodePoint code)
   else if ((code & 0xfffff800) == 0) return 2;
   else if ((code & 0xffff0000) == 0) return 3;
   else if ((code & 0xffe00000) == 0) return 4;
+#ifndef USE_RFC3629_RANGE
   else if ((code & 0xfc000000) == 0) return 5;
   else if ((code & 0x80000000) == 0) return 6;
+#endif
 #ifdef USE_INVALID_CODE_SCHEME
   else if (code == INVALID_CODE_FE) return 1;
   else if (code == INVALID_CODE_FF) return 1;
@@ -186,6 +170,7 @@ code_to_mbc(OnigCodePoint code, UChar *buf)
       *p++ = UTF8_TRAILS(code, 12);
       *p++ = UTF8_TRAILS(code,  6);
     }
+#ifndef USE_RFC3629_RANGE
     else if ((code & 0xfc000000) == 0) {
       *p++ = (UChar )(((code>>24) & 0x03) | 0xf8);
       *p++ = UTF8_TRAILS(code, 18);
@@ -199,6 +184,7 @@ code_to_mbc(OnigCodePoint code, UChar *buf)
       *p++ = UTF8_TRAILS(code, 12);
       *p++ = UTF8_TRAILS(code,  6);
     }
+#endif
 #ifdef USE_INVALID_CODE_SCHEME
     else if (code == INVALID_CODE_FE) {
       *p = 0xfe;
@@ -214,13 +200,13 @@ code_to_mbc(OnigCodePoint code, UChar *buf)
     }
 
     *p++ = UTF8_TRAIL0(code);
-    return p - buf;
+    return (int )(p - buf);
   }
 }
 
 static int
 mbc_case_fold(OnigCaseFoldType flag, const UChar** pp,
-	      const UChar* end, UChar* fold)
+              const UChar* end, UChar* fold)
 {
   const UChar* p = *pp;
 
@@ -242,50 +228,13 @@ mbc_case_fold(OnigCaseFoldType flag, const UChar** pp,
   }
   else {
     return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF8, flag,
-					 pp, end, fold);
+                                         pp, end, fold);
   }
 }
 
-#if 0
-static int
-is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
-{
-  const UChar* p = *pp;
-
-  if (ONIGENC_IS_MBC_ASCII(p)) {
-    (*pp)++;
-    return ONIGENC_IS_ASCII_CODE_CASE_AMBIG(*p);
-  }
-  else {
-    (*pp) += enclen(ONIG_ENCODING_UTF8, p);
-
-    if (*p == 0xc3) {
-      int c = *(p + 1);
-      if (c >= 0x80) {
-        if (c <= (UChar )0x9e) { /* upper */
-          if (c == (UChar )0x97) return FALSE;
-          return TRUE;
-        }
-        else if (c >= (UChar )0xa0 && c <= (UChar )0xbe) { /* lower */
-          if (c == (UChar )'\267') return FALSE;
-          return TRUE;
-        }
-        else if (c == (UChar )0x9f &&
-                 (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
-          return TRUE;
-        }
-      }
-    }
-  }
-
-  return FALSE;
-}
-#endif
-
-
 static int
 get_ctype_code_range(OnigCtype ctype, OnigCodePoint *sb_out,
-		     const OnigCodePoint* ranges[])
+                     const OnigCodePoint* ranges[])
 {
   *sb_out = 0x80;
   return onigenc_unicode_ctype_code_range(ctype, ranges);
@@ -309,15 +258,19 @@ get_case_fold_codes_by_str(OnigCaseFoldType flag,
     const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
 {
   return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF8,
-						    flag, p, end, items);
+                                                    flag, p, end, items);
 }
 
 OnigEncodingType OnigEncodingUTF8 = {
   mbc_enc_len,
   "UTF-8",     /* name */
-  6,           /* max byte length */
-  1,           /* min byte length */
-  is_mbc_newline,
+#ifdef USE_RFC3629_RANGE
+  4,           /* max enc length */
+#else
+  6,
+#endif
+  1,           /* min enc length */
+  onigenc_is_mbc_newline_0x0a,
   mbc_to_code,
   code_to_mbclen,
   code_to_mbc,
@@ -331,5 +284,7 @@ OnigEncodingType OnigEncodingUTF8 = {
   onigenc_always_true_is_allowed_reverse_match,
   NULL, /* init */
   NULL, /* is_initialized */
-  is_valid_mbc_string
+  is_valid_mbc_string,
+  ENC_FLAG_ASCII_COMPATIBLE|ENC_FLAG_UNICODE|ENC_FLAG_SKIP_OFFSET_1_OR_0,
+  0, 0
 };

package/deps/jq/modules/oniguruma/test/CMakeLists.txt

@@ -0,0 +1,55 @@
+if(MSVC)
+  if(MSVC_VERSION LESS "1900")
+    # < VS2015, no "/utf-8" option, can not build test
+    return()
+  endif()
+endif()
+
+enable_testing()
+
+add_executable(test_utf8 test_utf8.c)
+target_link_libraries(test_utf8 onig)
+if(MSVC)
+  target_compile_options(test_utf8 PRIVATE /utf-8)
+endif(MSVC)
+
+add_executable(test_syntax test_syntax.c)
+target_link_libraries(test_syntax onig)
+if(MSVC)
+  target_compile_options(test_syntax PRIVATE /utf-8)
+endif(MSVC)
+
+add_executable(test_options test_options.c)
+target_link_libraries(test_options onig)
+if(MSVC)
+  target_compile_options(test_options PRIVATE /utf-8)
+endif(MSVC)
+
+if(NOT MSVC)
+  # EUC
+  add_executable(testc testc.c)
+  target_link_libraries(testc onig)
+  if (CMAKE_C_COMPILER_ID MATCHES "Clang|GNU")
+	target_compile_options(testc PRIVATE -Wall -Wno-invalid-source-encoding)
+  endif()
+endif(NOT MSVC)
+
+if(ENABLE_POSIX_API)
+  add_executable(testp testp.c)
+  target_link_libraries(testp onig)
+endif()
+
+add_executable(testcu testu.c)
+target_link_libraries(testcu onig)
+
+add_executable(test_regset test_regset.c)
+target_link_libraries(test_regset onig)
+if(MSVC)
+  target_compile_options(test_regset PRIVATE /utf-8)
+endif(MSVC)
+
+add_executable(test_back test_back.c)
+target_link_libraries(test_back onig)
+if(MSVC)
+  target_compile_options(test_back PRIVATE /utf-8)
+endif(MSVC)

package/deps/jq/modules/oniguruma/test/Makefile.am

@@ -1,28 +1,83 @@
 ## Makefile.am for Oniguruma
 lib_onig = ../src/libonig.la
 
-AM_LDFLAGS  = -L$(prefix)/lib
-AM_CFLAGS =
-AM_CPPFLAGS = -I../src -I$(includedir)
+AM_LDFLAGS  = -L$(libdir)
+AM_CFLAGS = -Wall -Wno-invalid-source-encoding
+AM_CPPFLAGS = -I$(top_srcdir)/src
 
-TESTS = testc testp testcu
+if ENABLE_POSIX_API
+TESTS = test_utf8 test_syntax test_options testc testp testcu test_regset test_back
+else
+TESTS = test_utf8 test_syntax test_options testc testcu test_regset test_back
+endif
 
-check_PROGRAMS = testc testp testcu
+check_PROGRAMS = $(TESTS)
 
-test: testc testp testcu
-	@echo "[Oniguruma API, ASCII/EUC-JP check]"
+test: test_uchar test_regex_t $(TESTS)
+	@echo "[Oniguruma API, UTF-8 check]"
+	@./test_utf8  | grep RESULT
+	@echo "[Oniguruma API, SYNTAX check]"
+	@./test_syntax  | grep RESULT
+	@echo "[Oniguruma API, Options check]"
+	@./test_options  | grep RESULT
+	@echo "[Oniguruma API, EUC-JP check]"
 	@./testc  | grep RESULT
-	@echo "[POSIX API, ASCII/EUC-JP check]"
+if ENABLE_POSIX_API
+	@echo "[POSIX API, UTF-8 check]"
 	@./testp  | grep RESULT
+endif
 	@echo "[Oniguruma API, UTF-16 check]"
 	@./testcu | grep RESULT
+	@echo ""
+	@echo "[Oniguruma API, regset check]"
+	@./test_regset
+	@echo "[Oniguruma API, backward search check]"
+	@./test_back  | grep RESULT
+
+test_uchar:
+	@echo "[UChar in oniguruma.h check]"
+	@grep "\(^\|[^g]\)UChar" $(top_srcdir)/src/oniguruma.h
+	@echo ""
+
+test_regex_t:
+	@echo "[regex_t in oniguruma.h check]"
+	@grep "\(^\|[^[:alnum:]]\)regex_t" $(top_srcdir)/src/oniguruma.h
+	@echo ""
+
+
+test_utf8_SOURCES = test_utf8.c
+test_utf8_LDADD = $(lib_onig)
+
+test_syntax_SOURCES = test_syntax.c
+test_syntax_LDADD = $(lib_onig)
+
+test_options_SOURCES = test_options.c
+test_options_LDADD = $(lib_onig)
 
 testc_SOURCES = testc.c
 testc_LDADD = $(lib_onig)
 
-testp_SOURCES = testc.c
+testp_SOURCES = testp.c
 testp_LDADD = $(lib_onig)
-testp_CFLAGS = -DPOSIX_TEST
 
 testcu_SOURCES = testu.c
 testcu_LDADD = $(lib_onig)
+
+test_regset_SOURCES = test_regset.c
+test_regset_LDADD = $(lib_onig)
+
+test_back_SOURCES = test_back.c
+test_back_LDADD = $(lib_onig)
+
+
+gcov:
+	make CFLAGS="--coverage" test_utf8
+	make CFLAGS="--coverage" test_syntax
+	make CFLAGS="--coverage" test_options
+	make CFLAGS="--coverage" testc
+if ENABLE_POSIX_API
+	make CFLAGS="--coverage" testp
+endif
+	make CFLAGS="--coverage" testcu
+	make CFLAGS="--coverage" test_regset
+	make CFLAGS="--coverage" test_back

package/deps/jq/modules/oniguruma/test/test.sh

@@ -0,0 +1,17 @@
+#!/bin/sh
+
+echo "[Oniguruma API, UTF-8 check]"
+./test_utf8  | grep RESULT
+echo "[Oniguruma API, SYNTAX check]"
+./test_syntax  | grep RESULT
+echo "[Oniguruma API, Options check]"
+./test_options  | grep RESULT
+echo "[Oniguruma API, EUC-JP check]"
+./testc  | grep RESULT
+echo "[Oniguruma API, UTF-16 check]"
+./testcu | grep RESULT
+echo ""
+echo "[Oniguruma API, regset check]"
+./test_regset
+echo "[Oniguruma API, backward search check]"
+./test_back  | grep RESULT