Add trim/0, ltrim/0 and rtrim/0 that trims leading and trailing whitespace

Author: wader

docs/content/manual/manual.yml

@@ -1772,6 +1772,25 @@ sections:
             input: '["fo", "foo", "barfoo", "foobar", "foob"]'
             output: ['["fo","","bar","foobar","foob"]']
 
+      - title: "`trim`, `ltrim`, `rtrim`"
+        body: |
+
+          `trim` trims both leading and trailing whitespace.
+
+          `ltrim` trims only leading (left side) whitespace.
+
+          `rtrim` trims only trailing (right side) whitespace.
+
+          Whitespace characters are the usual `" "`, `"\n"` `"\t"`, `"\r"`
+          and also all characters in the Unicode character database with the
+          whitespace property. Note that what considers whitespace might
+          change in the future.
+
+        examples:
+          - program: 'trim, ltrim, rtrim'
+            input: '" abc "'
+            output: ['"abc"', '"abc "', '" abc"']
+
       - title: "`explode`"
         body: |
 

jq.1.prebuilt

@@ -1197,6 +1197,58 @@ static jv f_string_indexes(jq_state *jq, jv a, jv b) {
   return jv_string_indexes(a, b);
 }
 
+enum trim_op {
+  TRIM_LEFT  = 1 << 0,
+  TRIM_RIGHT = 1 << 1
+};
+
+static jv string_trim(jv a, int op) {
+  if (jv_get_kind(a) != JV_KIND_STRING) {
+    return ret_error(a, jv_string("trim input must be a string"));
+  }
+
+  int len = jv_string_length_bytes(jv_copy(a));
+  const char *start = jv_string_value(a);
+  const char *trim_start = start;
+  const char *end = trim_start + len;
+  const char *trim_end = end;
+  int c;
+
+  if (op & TRIM_LEFT) {
+    for (;;) {
+      const char *ns = jvp_utf8_next(trim_start, end, &c);
+      if (!ns || !jvp_codepoint_is_whitespace(c))
+        break;
+      trim_start = ns;
+    }
+  }
+
+  // make sure not empty string or start trim has trimmed everything
+  if ((op & TRIM_RIGHT) && trim_end > trim_start) {
+    for (;;) {
+      const char *ns = jvp_utf8_backtrack(trim_end-1, trim_start, NULL);
+      jvp_utf8_next(ns, trim_end, &c);
+      if (!jvp_codepoint_is_whitespace(c))
+        break;
+      trim_end = ns;
+      if (ns == trim_start)
+        break;
+    }
+  }
+
+  // no new string needed if there is nothing to trim
+  if (trim_start == start && trim_end == end)
+    return a;
+
+  jv ts = jv_string_sized(trim_start, trim_end - trim_start);
+  jv_free(a);
+  return ts;
+}
+
+static jv f_string_trim(jq_state *jq, jv a)  { return string_trim(a, TRIM_LEFT | TRIM_RIGHT); }
+static jv f_string_ltrim(jq_state *jq, jv a) { return string_trim(a, TRIM_LEFT); }
+static jv f_string_rtrim(jq_state *jq, jv a) { return string_trim(a, TRIM_RIGHT); }
+
 static jv f_string_implode(jq_state *jq, jv a) {
   if (jv_get_kind(a) != JV_KIND_ARRAY) {
     return ret_error(a, jv_string("implode input must be an array"));
@@ -1721,6 +1773,9 @@ BINOPS
   {f_string_explode, "explode", 1},
   {f_string_implode, "implode", 1},
   {f_string_indexes, "_strindices", 2},
+  {f_string_trim, "trim", 1},
+  {f_string_ltrim, "ltrim", 1},
+  {f_string_rtrim, "rtrim", 1},
   {f_setpath, "setpath", 3}, // FIXME typechecking
   {f_getpath, "getpath", 2},
   {f_delpaths, "delpaths", 2},

src/builtin.c

@@ -118,3 +118,21 @@ int jvp_utf8_encode(int codepoint, char* out) {
   assert(out - start == jvp_utf8_encode_length(codepoint));
   return out - start;
 }
+
+// characters with White_Space property in:
+// https://www.unicode.org/Public/UCD/latest/ucd/PropList.txt
+int jvp_codepoint_is_whitespace(int c) {
+  return
+    (c >= 0x0009 && c <= 0x000D) || // <control-0009>..<control-000D>
+    c == 0x0020                  || // SPACE
+    c == 0x0085                  || // <control-0085>
+    c == 0x00A0                  || // NO-BREAK SPACE
+    c == 0x1680                  || // OGHAM SPACE MARK
+    (c >= 0x2000 && c <= 0x200A) || // EN QUAD..HAIR SPACE
+    c == 0x2028                  || // LINE SEPARATOR
+    c == 0x2029                  || // PARAGRAPH SEPARATOR
+    c == 0x202F                  || // NARROW NO-BREAK SPACE
+    c == 0x205F                  || // MEDIUM MATHEMATICAL SPACE
+    c == 0x3000                     // IDEOGRAPHIC SPACE
+    ;
+}

src/jv_unicode.c

@@ -9,4 +9,6 @@ int jvp_utf8_decode_length(char startchar);
 
 int jvp_utf8_encode_length(int codepoint);
 int jvp_utf8_encode(int codepoint, char* out);
+
+int jvp_codepoint_is_whitespace(int c);
 #endif

src/jv_unicode.h

@@ -1334,6 +1334,26 @@ split("")
 "xababababax"
 [1,7,[1,3,5,7]]
 
+# trim
+# \u000b is vertical tab (\v not supported by json)
+map(trim), map(ltrim), map(rtrim)
+[" \n\t\r\f\u000b", "","  ", "a", " a ", "abc", "  abc  ", "  abc", "abc  "]
+["", "", "", "a", "a", "abc", "abc", "abc", "abc"]
+["", "", "", "a", "a ", "abc", "abc  ", "abc", "abc  "]
+["", "", "", "a", " a", "abc", "  abc", "  abc", "abc"]
+
+trim, ltrim, rtrim
+"\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u2028\u2029\u202F\u205F\u3000abc\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u2028\u2029\u202F\u205F\u3000"
+"abc"
+"abc\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u2028\u2029\u202F\u205F\u3000"
+"\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u2028\u2029\u202F\u205F\u3000abc"
+
+try trim catch ., try ltrim catch ., try rtrim catch .
+123
+"trim input must be a string"
+"trim input must be a string"
+"trim input must be a string"
+
 indices(1)
 [0,1,1,2,3,4,1,5]
 [1,2,6]