@port-labs/jq-node-bindings 0.0.13 → 0.0.15-dev1

package/deps/jq/modules/oniguruma/src/koi8.c

@@ -2,7 +2,7 @@
   koi8.c -  Oniguruma (regular expression library)
 **********************************************************************/
 /*-
- * Copyright (c) 2002-2016  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
@@ -105,34 +105,19 @@ static const unsigned short EncKOI8_CtypeTable[256] = {
 
 
 static int
-koi8_mbc_case_fold(OnigCaseFoldType flag ARG_UNUSED,
-	   const UChar** pp, const UChar* end ARG_UNUSED, UChar* lower)
+koi8_mbc_case_fold(OnigCaseFoldType flag,
+                   const UChar** pp, const UChar* end ARG_UNUSED, UChar* lower)
 {
   const UChar* p = *pp;
 
-  *lower = ENC_KOI8_TO_LOWER_CASE(*p);
-  (*pp)++;
-  return 1;
-}
-
-#if 0
-static int
-koi8_is_mbc_ambiguous(OnigAmbigType flag, const OnigUChar** pp, const OnigUChar* end)
-{
-  const OnigUChar* p = *pp;
+  if (CASE_FOLD_IS_NOT_ASCII_ONLY(flag) || ONIGENC_IS_ASCII_CODE(*p))
+    *lower = ENC_KOI8_TO_LOWER_CASE(*p);
+  else
+    *lower = *p;
 
   (*pp)++;
-  if (((flag & ONIGENC_CASE_FOLD_ASCII_CASE) != 0 &&
-       ONIGENC_IS_MBC_ASCII(p)) ||
-      ((flag & ONIGENC_CASE_FOLD_NONASCII_CASE) != 0 &&
-       !ONIGENC_IS_MBC_ASCII(p))) {
-    int v = (EncKOI8_CtypeTable[*p] &
-             (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
-    return (v != 0 ? TRUE : FALSE);
-  }
-  return FALSE;
+  return 1;
 }
-#endif
 
 static int
 koi8_is_code_ctype(OnigCodePoint code, unsigned int ctype)
@@ -214,7 +199,7 @@ static const OnigPairCaseFoldCodes CaseFoldMap[] = {
 
 static int
 koi8_apply_all_case_fold(OnigCaseFoldType flag,
-			 OnigApplyAllCaseFoldFunc f, void* arg)
+                         OnigApplyAllCaseFoldFunc f, void* arg)
 {
   return onigenc_apply_all_case_fold_with_map(
              sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0,
@@ -226,8 +211,8 @@ koi8_get_case_fold_codes_by_str(OnigCaseFoldType flag,
     const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
 {
   return onigenc_get_case_fold_codes_by_str_with_map(
-	     sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0,
-	     flag, p, end, items);
+                 sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0,
+                 flag, p, end, items);
 }
 
 OnigEncodingType OnigEncodingKOI8 = {
@@ -249,5 +234,7 @@ OnigEncodingType OnigEncodingKOI8 = {
   onigenc_always_true_is_allowed_reverse_match,
   NULL, /* init */
   NULL, /* is_initialized */
-  onigenc_always_true_is_valid_mbc_string
+  onigenc_always_true_is_valid_mbc_string,
+  ENC_FLAG_ASCII_COMPATIBLE|ENC_FLAG_SKIP_OFFSET_1,
+  0, 0
 };

package/deps/jq/modules/oniguruma/src/koi8_r.c

@@ -2,7 +2,7 @@
   koi8_r.c -  Oniguruma (regular expression library)
 **********************************************************************/
 /*-
- * Copyright (c) 2002-2016  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
@@ -109,23 +109,14 @@ koi8_r_mbc_case_fold(OnigCaseFoldType flag ARG_UNUSED,
 {
   const UChar* p = *pp;
 
-  *lower = ENC_KOI8_R_TO_LOWER_CASE(*p);
-  (*pp)++;
-  return 1;
-}
-
-#if 0
-static int
-koi8_r_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
-{
-  int v;
-  const UChar* p = *pp;
+  if (CASE_FOLD_IS_NOT_ASCII_ONLY(flag) || ONIGENC_IS_ASCII_CODE(*p))
+    *lower = ENC_KOI8_R_TO_LOWER_CASE(*p);
+  else
+    *lower = *p;
 
   (*pp)++;
-  v = (EncKOI8_R_CtypeTable[*p] & (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
-  return (v != 0 ? TRUE : FALSE);
+  return 1;
 }
-#endif
 
 static int
 koi8_r_is_code_ctype(OnigCodePoint code, unsigned int ctype)
@@ -176,7 +167,7 @@ static const OnigPairCaseFoldCodes CaseFoldMap[] = {
 
 static int
 koi8_r_apply_all_case_fold(OnigCaseFoldType flag,
-			       OnigApplyAllCaseFoldFunc f, void* arg)
+                           OnigApplyAllCaseFoldFunc f, void* arg)
 {
   return onigenc_apply_all_case_fold_with_map(
              sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0,
@@ -188,8 +179,8 @@ koi8_r_get_case_fold_codes_by_str(OnigCaseFoldType flag,
     const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
 {
   return onigenc_get_case_fold_codes_by_str_with_map(
-	     sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0,
-	     flag, p, end, items);
+                 sizeof(CaseFoldMap)/sizeof(OnigPairCaseFoldCodes), CaseFoldMap, 0,
+                 flag, p, end, items);
 }
 
 OnigEncodingType OnigEncodingKOI8_R = {
@@ -211,5 +202,7 @@ OnigEncodingType OnigEncodingKOI8_R = {
   onigenc_always_true_is_allowed_reverse_match,
   NULL, /* init */
   NULL, /* is_initialized */
-  onigenc_always_true_is_valid_mbc_string
+  onigenc_always_true_is_valid_mbc_string,
+  ENC_FLAG_ASCII_COMPATIBLE|ENC_FLAG_SKIP_OFFSET_1,
+  0, 0
 };

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

@@ -0,0 +1,21 @@
+#!/bin/sh
+
+GPERF=gperf
+SED=sed
+
+TMP1=gperf1.tmp
+TMP2=gperf2.tmp
+
+GPERF_OPT='-pt -T -L ANSI-C'
+
+ADD_CAST='s/return +len +\+ +asso_values/return (unsigned int )len + asso_values/'
+
+${GPERF} ${GPERF_OPT} -N onigenc_euc_jp_lookup_property_name --output-file ${TMP1} euc_jp_prop.gperf
+cat ${TMP1} | ${SED} -E "${ADD_CAST}" > euc_jp_prop.c
+
+${GPERF} ${GPERF_OPT} -N onigenc_sjis_lookup_property_name --output-file ${TMP2} sjis_prop.gperf
+cat ${TMP2} | ${SED} -E "${ADD_CAST}" > sjis_prop.c
+
+rm -f ${TMP1} ${TMP2}
+
+exit 0

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

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

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

@@ -0,0 +1,267 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+# make_unicode_egcb_data.py
+# Copyright (c) 2017-2022  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('GraphemeBreakProperty.txt')
+merge_dic(DIC, dic)
+merge_props(PROPS, props)
+
+PROPS = sorted(PROPS)
+
+print '/* unicode_egcb_data.c: Generated by make_unicode_egcb_data.py. */'
+COPYRIGHT = '''
+/*-
+ * Copyright (c) 2017-2022  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 GRAPHEME_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 EGCB_RANGE_NUM = %d;" % num_ranges
+
+print 'static EGCB_RANGE_TYPE EGCB_RANGES[] = {'
+for i, (start, end, prop) in enumerate(ranges):
+  if i == num_ranges - 1:
+    comma = ''
+  else:
+    comma = ','
+
+  type_name = 'EGCB_' + prop
+  print " {0x%06x, 0x%06x, %s }%s" % (start, end, type_name, comma)
+
+print '};'
+
+sys.exit(0)

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

@@ -1,22 +1,36 @@
 #!/bin/sh
 
-TMP=gperf.tmp
+GPERF=gperf
+
+TMP0=gperf0.tmp
+TMP1=gperf1.tmp
+TMP2=gperf2.tmp
+TMP3=gperf3.tmp
+
 GPERF_OPT='-n -C -T -c -t -j1 -L ANSI-C '
 
-./make_unicode_fold_data.py > unicode_fold_data.c
+python2 make_unicode_fold_data.py > unicode_fold_data.c
+
+${GPERF} ${GPERF_OPT} -F,-1,0 -N onigenc_unicode_unfold_key unicode_unfold_key.gperf > ${TMP0}
+python2 gperf_unfold_key_conv.py < ${TMP0} > unicode_unfold_key.c
 
-gperf ${GPERF_OPT} -F,-1,0 -N unicode_unfold_key unicode_unfold_key.gperf > ${TMP}
-./gperf_unfold_key_conv.py < ${TMP} > unicode_unfold_key.c
+${GPERF} ${GPERF_OPT} -F,-1 -N onigenc_unicode_fold1_key unicode_fold1_key.gperf > ${TMP1}
+python2 gperf_fold_key_conv.py 1 < ${TMP1} > unicode_fold1_key.c
 
-gperf ${GPERF_OPT} -F,-1 -N unicode_fold1_key unicode_fold1_key.gperf > ${TMP}
-./gperf_fold_key_conv.py 1 < ${TMP} > unicode_fold1_key.c
+${GPERF} ${GPERF_OPT} -F,-1 -N onigenc_unicode_fold2_key unicode_fold2_key.gperf > ${TMP2}
+python2 gperf_fold_key_conv.py 2 < ${TMP2} > unicode_fold2_key.c
 
-gperf ${GPERF_OPT} -F,-1 -N unicode_fold2_key unicode_fold2_key.gperf > ${TMP}
-./gperf_fold_key_conv.py 2 < ${TMP} > unicode_fold2_key.c
+${GPERF} ${GPERF_OPT} -F,-1 -N onigenc_unicode_fold3_key unicode_fold3_key.gperf > ${TMP3}
+python2 gperf_fold_key_conv.py 3 < ${TMP3} > unicode_fold3_key.c
 
-gperf ${GPERF_OPT} -F,-1 -N unicode_fold3_key unicode_fold3_key.gperf > ${TMP}
-./gperf_fold_key_conv.py 3 < ${TMP} > unicode_fold3_key.c
+# remove redundant EOLs before EOF
+perl -i -pe 'BEGIN{undef $/}s/\n\n*\z/\n/;' unicode_fold_data.c
+perl -i -pe 'BEGIN{undef $/}s/\n\n*\z/\n/;' unicode_fold1_key.c
+perl -i -pe 'BEGIN{undef $/}s/\n\n*\z/\n/;' unicode_fold2_key.c
+perl -i -pe 'BEGIN{undef $/}s/\n\n*\z/\n/;' unicode_fold3_key.c
+perl -i -pe 'BEGIN{undef $/}s/\n\n*\z/\n/;' unicode_unfold_key.c
 
-rm -f ${TMP}
+rm -f ${TMP0} ${TMP1} ${TMP2} ${TMP3}
+rm -f unicode_unfold_key.gperf unicode_fold1_key.gperf unicode_fold2_key.gperf unicode_fold3_key.gperf
 
 exit 0