@port-labs/jq-node-bindings 0.0.14 → 0.0.15-dev2

package/deps/jq/modules/oniguruma/src/make_unicode_wb.sh

@@ -0,0 +1,7 @@
+#!/bin/sh
+
+NAME=unicode_wb_data
+
+python2 make_unicode_wb_data.py > ${NAME}.c
+
+exit 0

package/deps/jq/modules/oniguruma/src/make_unicode_wb_data.py

@@ -0,0 +1,267 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+# make_unicode_wb_data.py
+# Copyright (c) 2019-2022  K.Kosako
+
+import sys
+import re
+
+MAX_CODE_POINT = 0x10ffff
+
+PR_TOTAL_REG = re.compile("#\s*Total\s+(?:code\s+points|elements):")
+PR_LINE_REG  = re.compile("([0-9A-Fa-f]+)(?:..([0-9A-Fa-f]+))?\s*;\s*(\w+)")
+PA_LINE_REG  = re.compile("(\w+)\s*;\s*(\w+)")
+PVA_LINE_REG = re.compile("(sc|gc)\s*;\s*(\w+)\s*;\s*(\w+)(?:\s*;\s*(\w+))?")
+BL_LINE_REG  = re.compile("([0-9A-Fa-f]+)\.\.([0-9A-Fa-f]+)\s*;\s*(.*)")
+VERSION_REG  = re.compile("#\s*.*-(\d+)\.(\d+)\.(\d+)\.txt")
+
+VERSION_INFO = [-1, -1, -1]
+DIC  = { }
+PROPS = []
+PropIndex = { }
+
+def check_version_info(s):
+  m = VERSION_REG.match(s)
+  if m is not None:
+    VERSION_INFO[0] = int(m.group(1))
+    VERSION_INFO[1] = int(m.group(2))
+    VERSION_INFO[2] = int(m.group(3))
+
+def print_ranges(ranges):
+  for (start, end) in ranges:
+    print "0x%06x, 0x%06x" % (start, end)
+
+def print_prop_and_index(prop, i):
+  print "%-35s %3d" % (prop + ',', i)
+  PropIndex[prop] = i
+
+def dic_find_by_value(dic, v):
+  for key, val in dic.items():
+    if val == v:
+      return key
+
+  return None
+
+
+def normalize_ranges(in_ranges, sort=False):
+  if sort:
+    ranges = sorted(in_ranges)
+  else:
+    ranges = in_ranges
+
+  r = []
+  prev = None
+  for (start, end) in ranges:
+    if prev >= start - 1:
+      (pstart, pend) = r.pop()
+      end = max(pend, end)
+      start = pstart
+
+    r.append((start, end))
+    prev = end
+
+  return r
+
+def inverse_ranges(in_ranges):
+  r = []
+  prev = 0x000000
+  for (start, end) in in_ranges:
+    if prev < start:
+      r.append((prev, start - 1))
+
+    prev = end + 1
+
+  if prev < MAX_CODE_POINT:
+    r.append((prev, MAX_CODE_POINT))
+
+  return r
+
+def add_ranges(r1, r2):
+  r = r1 + r2
+  return normalize_ranges(r, True)
+
+def sub_one_range(one_range, rs):
+  r = []
+  (s1, e1) = one_range
+  n = len(rs)
+  for i in range(0, n):
+    (s2, e2) = rs[i]
+    if s2 >= s1 and s2 <= e1:
+      if s2 > s1:
+        r.append((s1, s2 - 1))
+      if e2 >= e1:
+        return r
+
+      s1 = e2 + 1
+    elif s2 < s1 and e2 >= s1:
+      if e2 < e1:
+        s1 = e2 + 1
+      else:
+        return r
+
+  r.append((s1, e1))
+  return r
+
+def sub_ranges(r1, r2):
+  r = []
+  for one_range in r1:
+    rs = sub_one_range(one_range, r2)
+    r.extend(rs)
+
+  return r
+
+def add_ranges_in_dic(dic):
+  r = []
+  for k, v in dic.items():
+    r = r + v
+
+  return normalize_ranges(r, True)
+
+def normalize_ranges_in_dic(dic, sort=False):
+  for k, v in dic.items():
+    r = normalize_ranges(v, sort)
+    dic[k] = r
+
+def merge_dic(to_dic, from_dic):
+  to_keys   = to_dic.keys()
+  from_keys = from_dic.keys()
+  common = list(set(to_keys) & set(from_keys))
+  if len(common) != 0:
+    print >> sys.stderr, "merge_dic: collision: %s" % sorted(common)
+
+  to_dic.update(from_dic)
+
+def merge_props(to_props, from_props):
+  common = list(set(to_props) & set(from_props))
+  if len(common) != 0:
+    print >> sys.stderr, "merge_props: collision: %s" % sorted(common)
+
+  to_props.extend(from_props)
+
+def add_range_into_dic(dic, name, start, end):
+  d = dic.get(name, None)
+  if d is None:
+    d = [(start, end)]
+    dic[name] = d
+  else:
+    d.append((start, end))
+
+def list_sub(a, b):
+  x = set(a) - set(b)
+  return list(x)
+
+def parse_properties(path):
+  with open(path, 'r') as f:
+    dic = { }
+    prop = None
+    props = []
+    for line in f:
+      s = line.strip()
+      if len(s) == 0:
+        continue
+
+      if s[0] == '#':
+        if VERSION_INFO[0] < 0:
+          check_version_info(s)
+
+      m = PR_LINE_REG.match(s)
+      if m:
+        prop = m.group(3)
+        if m.group(2):
+          start = int(m.group(1), 16)
+          end   = int(m.group(2), 16)
+          add_range_into_dic(dic, prop, start, end)
+        else:
+          start = int(m.group(1), 16)
+          add_range_into_dic(dic, prop, start, start)
+
+      elif PR_TOTAL_REG.match(s) is not None:
+        props.append(prop)
+
+  normalize_ranges_in_dic(dic)
+  return (dic, props)
+
+
+### main ###
+argv = sys.argv
+argc = len(argv)
+
+dic, props = parse_properties('WordBreakProperty.txt')
+merge_dic(DIC, dic)
+merge_props(PROPS, props)
+
+PROPS = sorted(PROPS)
+
+print '/* unicode_wb_data.c: Generated by make_unicode_wb_data.py. */'
+COPYRIGHT = '''
+/*-
+ * Copyright (c) 2019-2022  K.Kosako
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+'''.strip()
+
+print COPYRIGHT
+print ''
+if VERSION_INFO[0] < 0:
+  raise RuntimeError("Version is not found.")
+
+print "#define WORD_BREAK_PROPERTY_VERSION  %02d%02d%02d" % (VERSION_INFO[0], VERSION_INFO[1], VERSION_INFO[2])
+print ''
+
+ranges = []
+for prop in PROPS:
+  rs = DIC[prop]
+  for (start, end) in rs:
+    ranges.append((start, end, prop))
+
+ranges = sorted(ranges, key=lambda x: x[0])
+
+prev = -1
+for (start, end, prop) in ranges:
+  if prev >= start:
+    raise ValueError("{2}:{0} - {1} range overlap prev value {3}".format(start, end, prop, prev))
+
+
+print '/*'
+for prop in PROPS:
+  print "%s" % prop
+print '*/'
+print ''
+
+num_ranges = len(ranges)
+print "static int WB_RANGE_NUM = %d;" % num_ranges
+
+print 'static WB_RANGE_TYPE WB_RANGES[] = {'
+for i, (start, end, prop) in enumerate(ranges):
+  if i == num_ranges - 1:
+    comma = ''
+  else:
+    comma = ','
+
+  type_name = 'WB_' + prop
+  print " {0x%06x, 0x%06x, %s }%s" % (start, end, type_name, comma)
+
+print '};'
+
+sys.exit(0)

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

@@ -2,7 +2,7 @@
   mktable.c
 **********************************************************************/
 /*-
- * Copyright (c) 2002-2016  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
+ * Copyright (c) 2002-2022  K.Kosako
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -269,7 +269,7 @@ static int IsBlank(int enc, int c)
   if (enc == ASCII)
     return isblank(c);
 
-  if (c == 0x09	|| c == 0x20) return 1;
+  if (c == 0x09 || c == 0x20) return 1;
 
   switch (enc) {
   case UNICODE_ISO_8859_1:
@@ -308,7 +308,7 @@ static int IsCntrl(int enc, int c)
   if (enc == ASCII)
     return iscntrl(c);
 
-  if (c >= 0x00	&& c <= 0x1F) return 1;
+  if (c >= 0x00 && c <= 0x1F) return 1;
 
   switch (enc) {
   case UNICODE_ISO_8859_1:
@@ -376,10 +376,10 @@ static int IsGraph(int enc, int c)
   case ISO_8859_3:
     if (c >= 0xa1) {
       if (c == 0xa5 || c == 0xae || c == 0xbe || c == 0xc3 || c == 0xd0 ||
-	  c == 0xe3 || c == 0xf0)
-	return 0;
+          c == 0xe3 || c == 0xf0)
+        return 0;
       else
-	return 1;
+        return 1;
     }
     break;
 
@@ -392,8 +392,8 @@ static int IsGraph(int enc, int c)
 
   case ISO_8859_7:
     if (c >= 0xa1 && c <= 0xfe &&
-	c != 0xa4 && c != 0xa5 && c != 0xaa &&
-	c != 0xae && c != 0xd2) return 1;
+        c != 0xa4 && c != 0xa5 && c != 0xaa &&
+        c != 0xae && c != 0xd2) return 1;
     break;
 
   case ISO_8859_8:
@@ -583,10 +583,10 @@ static int IsPrint(int enc, int c)
   case ISO_8859_3:
     if (c >= 0xa0) {
       if (c == 0xa5 || c == 0xae || c == 0xbe || c == 0xc3 || c == 0xd0 ||
-	  c == 0xe3 || c == 0xf0)
-	return 0;
+          c == 0xe3 || c == 0xf0)
+        return 0;
       else
-	return 1;
+        return 1;
     }
     break;
 
@@ -600,8 +600,8 @@ static int IsPrint(int enc, int c)
 
   case ISO_8859_7:
     if (c >= 0xa0 && c <= 0xfe &&
-	c != 0xa4 && c != 0xa5 && c != 0xaa &&
-	c != 0xae && c != 0xd2) return 1;
+        c != 0xa4 && c != 0xa5 && c != 0xaa &&
+        c != 0xae && c != 0xd2) return 1;
     break;
 
   case ISO_8859_8:
@@ -638,24 +638,28 @@ static int IsPunct(int enc, int c)
   if (enc == ASCII)
     return ispunct(c);
 
-  if (enc == UNICODE_ISO_8859_1) {
-    if (c == 0x24 || c == 0x2b || c == 0x5e || c == 0x60 ||
-        c == 0x7c || c == 0x7e) return 1;
-    if (c >= 0x3c && c <= 0x3e) return 1;
-  }
-
   if (c >= 0x21 && c <= 0x2f) return 1;
   if (c >= 0x3a && c <= 0x40) return 1;
   if (c >= 0x5b && c <= 0x60) return 1;
   if (c >= 0x7b && c <= 0x7e) return 1;
 
+  if (enc == UNICODE_ISO_8859_1) {
+    if (c < 0x80) return 0;
+
+    if (c >= 0xa1 && c <= 0xa9) return 1;
+    if (c >= 0xab && c <= 0xac) return 1;
+    if (c >= 0xae && c <= 0xb1) return 1;
+    if (c == 0xb4) return 1;
+    if (c >= 0xb6 && c <= 0xb8) return 1;
+    if (c == 0xbb || c == 0xbf || c == 0xd7 || c == 0xf7) return 1;
+    return 0;
+  }
+
   switch (enc) {
   case ISO_8859_1:
   case ISO_8859_9:
   case ISO_8859_15:
     if (c == 0xad) return 1;
-    /* fall */
-  case UNICODE_ISO_8859_1:
     if (c == 0xa1) return 1;
     if (c == 0xab) return 1;
     if (c == 0xb7) return 1;
@@ -1012,7 +1016,7 @@ static int IsWord(int enc, int c)
   case ISO_8859_10:
     if (c >= 0xa1 && c <= 0xff) {
       if (c != 0xa7 && c != 0xad && c != 0xb0 && c != 0xb7 && c != 0xbd)
-	return 1;
+        return 1;
     }
     break;
 
@@ -1037,7 +1041,7 @@ static int IsWord(int enc, int c)
   case ISO_8859_14:
     if (c >= 0xa1 && c <= 0xff) {
       if (c == 0xa3 || c == 0xa7 || c == 0xa9 || c == 0xad || c == 0xae ||
-	  c == 0xb6) return 0;
+          c == 0xb6) return 0;
       return 1;
     }
     break;
@@ -1102,7 +1106,7 @@ static int IsAscii(int enc ARG_UNUSED, int c)
 
 static int IsNewline(int enc ARG_UNUSED, int c)
 {
-  if (c == 0x0a) return 1;
+  if (c == NEWLINE_CODE) return 1;
   return 0;
 }
 

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

@@ -2,7 +2,7 @@
   onig_init.c -  Oniguruma (regular expression library)
 **********************************************************************/
 /*-
- * Copyright (c) 2016  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
+ * Copyright (c) 2016-2019  K.Kosako
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -27,7 +27,7 @@
  * SUCH DAMAGE.
  */
 
-#include "oniguruma.h"
+#include "regint.h"
 
 /* onig_init(): deprecated function */
 extern int

package/deps/jq/modules/oniguruma/src/oniggnu.h

@@ -4,7 +4,7 @@
   oniggnu.h - Oniguruma (regular expression library)
 **********************************************************************/
 /*-
- * Copyright (c) 2002-2005  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
@@ -35,10 +35,12 @@
 extern "C" {
 #endif
 
-#define RE_MBCTYPE_ASCII         0
-#define RE_MBCTYPE_EUC           1
-#define RE_MBCTYPE_SJIS          2
-#define RE_MBCTYPE_UTF8          3
+enum {
+  RE_MBCTYPE_ASCII = 0,
+  RE_MBCTYPE_EUC   = 1,
+  RE_MBCTYPE_SJIS  = 2,
+  RE_MBCTYPE_UTF8  = 3
+};
 
 /* GNU regex options */
 #ifndef RE_NREGS

package/deps/jq/modules/oniguruma/src/onigposix.h

@@ -4,7 +4,7 @@
   onigposix.h - Oniguruma (regular expression library)
 **********************************************************************/
 /*-
- * Copyright (c) 2002-2005  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
+ * Copyright (c) 2002-2020  K.Kosako
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -28,7 +28,9 @@
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE.
  */
-#include <stdlib.h>
+#ifndef ONIG_NO_STANDARD_C_HEADERS
+#include <stddef.h>
+#endif
 
 #ifdef __cplusplus
 extern "C" {
@@ -72,19 +74,19 @@ extern "C" {
 #define REG_POSIX_ENCODING_UTF16_LE  5
 
 
-typedef int regoff_t;
+typedef int onig_posix_regoff_t;
 
 typedef struct {
-  regoff_t  rm_so;
-  regoff_t  rm_eo;
-} regmatch_t;
+  onig_posix_regoff_t  rm_so;
+  onig_posix_regoff_t  rm_eo;
+} onig_posix_regmatch_t;
 
 /* POSIX regex_t */
 typedef struct {
   void*   onig;          /* Oniguruma regex_t*  */
   size_t  re_nsub;
   int     comp_options;
-} regex_t;
+} onig_posix_regex_t;
 
 
 #ifndef P_
@@ -95,9 +97,10 @@ typedef struct {
 #endif
 #endif
 
+#ifndef ONIG_STATIC
 #ifndef ONIG_EXTERN
 #if defined(_WIN32) && !defined(__GNUC__)
-#if defined(EXPORT)
+#if defined(ONIGURUMA_EXPORT)
 #define ONIG_EXTERN   extern __declspec(dllexport)
 #else
 #define ONIG_EXTERN   extern __declspec(dllimport)
@@ -108,6 +111,9 @@ typedef struct {
 #ifndef ONIG_EXTERN
 #define ONIG_EXTERN   extern
 #endif
+#else
+#define ONIG_EXTERN   extern
+#endif
 
 #ifndef ONIGURUMA_H
 typedef unsigned int        OnigOptionType;
@@ -128,6 +134,7 @@ ONIG_EXTERN OnigSyntaxType OnigSyntaxGnuRegex;
 ONIG_EXTERN OnigSyntaxType OnigSyntaxJava;
 ONIG_EXTERN OnigSyntaxType OnigSyntaxPerl;
 ONIG_EXTERN OnigSyntaxType OnigSyntaxRuby;
+ONIG_EXTERN OnigSyntaxType OnigSyntaxOniguruma;
 
 /* predefined syntaxes (see regsyntax.c) */
 #define ONIG_SYNTAX_POSIX_BASIC        (&OnigSyntaxPosixBasic)
@@ -138,6 +145,7 @@ ONIG_EXTERN OnigSyntaxType OnigSyntaxRuby;
 #define ONIG_SYNTAX_JAVA               (&OnigSyntaxJava)
 #define ONIG_SYNTAX_PERL               (&OnigSyntaxPerl)
 #define ONIG_SYNTAX_RUBY               (&OnigSyntaxRuby)
+#define ONIG_SYNTAX_ONIGURUMA          (&OnigSyntaxOniguruma)
 /* default syntax */
 #define ONIG_SYNTAX_DEFAULT             OnigDefaultSyntax
 
@@ -147,20 +155,36 @@ ONIG_EXTERN int  onig_set_default_syntax P_((OnigSyntaxType* syntax));
 ONIG_EXTERN void onig_copy_syntax P_((OnigSyntaxType* to, OnigSyntaxType* from));
 ONIG_EXTERN const char* onig_version P_((void));
 ONIG_EXTERN const char* onig_copyright P_((void));
+ONIG_EXTERN int onig_end P_((void));
 
 #endif /* ONIGURUMA_H */
 
 
-ONIG_EXTERN int    regcomp P_((regex_t* reg, const char* pat, int options));
-ONIG_EXTERN int    regexec P_((regex_t* reg, const char* str, size_t nmatch, regmatch_t* matches, int options));
-ONIG_EXTERN void   regfree P_((regex_t* reg));
-ONIG_EXTERN size_t regerror P_((int code, const regex_t* reg, char* buf, size_t size));
+ONIG_EXTERN int    onig_posix_regcomp P_((onig_posix_regex_t* reg, const char* pat, int options));
+ONIG_EXTERN int    onig_posix_regexec P_((onig_posix_regex_t* reg, const char* str, size_t nmatch, onig_posix_regmatch_t* matches, int options));
+ONIG_EXTERN void   onig_posix_regfree P_((onig_posix_regex_t* reg));
+ONIG_EXTERN size_t onig_posix_regerror P_((int code, const onig_posix_regex_t* reg, char* buf, size_t size));
 
 /* extended API */
-ONIG_EXTERN void reg_set_encoding P_((int enc));
-ONIG_EXTERN int  reg_name_to_group_numbers P_((regex_t* reg, const unsigned char* name, const unsigned char* name_end, int** nums));
-ONIG_EXTERN int  reg_foreach_name P_((regex_t* reg, int (*func)(const unsigned char*, const unsigned char*,int,int*,regex_t*,void*), void* arg));
-ONIG_EXTERN int  reg_number_of_names P_((regex_t* reg));
+ONIG_EXTERN void onig_posix_reg_set_encoding P_((int enc));
+ONIG_EXTERN int  onig_posix_reg_name_to_group_numbers P_((onig_posix_regex_t* reg, const unsigned char* name, const unsigned char* name_end, int** nums));
+ONIG_EXTERN int  onig_posix_reg_foreach_name P_((onig_posix_regex_t* reg, int (*func)(const unsigned char*, const unsigned char*,int,int*,onig_posix_regex_t*,void*), void* arg));
+ONIG_EXTERN int  onig_posix_reg_number_of_names P_((onig_posix_regex_t* reg));
+
+
+/* aliases */
+#define regex_t    onig_posix_regex_t
+#define regmatch_t onig_posix_regmatch_t
+#define regoff_t   onig_posix_regoff_t
+
+#define regcomp  onig_posix_regcomp
+#define regexec  onig_posix_regexec
+#define regfree  onig_posix_regfree
+#define regerror onig_posix_regerror
+#define reg_set_encoding          onig_posix_reg_set_encoding
+#define reg_name_to_group_numbers onig_posix_reg_name_to_group_numbers
+#define reg_foreach_name          onig_posix_reg_foreach_name
+#define reg_number_of_names       onig_posix_reg_number_of_names
 
 #ifdef __cplusplus
 }