From 232ea22dc55be28366b56147fd80ccff8ec1de46 Mon Sep 17 00:00:00 2001 From: Calvin Rose Date: Fri, 10 May 2019 16:09:49 -0400 Subject: [PATCH] Add string/triml, string/trimr, and string/trim. --- src/boot/boot.janet | 2 +- src/core/string.c | 72 +++++++++++++++++++++++++++++++++++++++++++++ test/suite2.janet | 10 +++++++ 3 files changed, 83 insertions(+), 1 deletion(-) diff --git a/src/boot/boot.janet b/src/boot/boot.janet index 6de2f326..18d007b4 100644 --- a/src/boot/boot.janet +++ b/src/boot/boot.janet @@ -1,5 +1,5 @@ # The core janet library -# Copyright 2019 (C) Calvin Rose +# Copyright 2019 © Calvin Rose ### ### diff --git a/src/core/string.c b/src/core/string.c index 86699c6d..e274d263 100644 --- a/src/core/string.c +++ b/src/core/string.c @@ -467,6 +467,60 @@ static Janet cfun_string_format(int32_t argc, Janet *argv) { return janet_stringv(buffer->data, buffer->count); } +static int trim_help_checkset(JanetByteView set, uint8_t x) { + for (int32_t j = 0; j < set.len; j++) + if (set.bytes[j] == x) + return 1; + return 0; +} + +static int32_t trim_help_leftedge(JanetByteView str, JanetByteView set) { + for (int32_t i = 0; i < str.len; i++) + if (!trim_help_checkset(set, str.bytes[i])) + return i; + return str.len; +} + +static int32_t trim_help_rightedge(JanetByteView str, JanetByteView set) { + for (int32_t i = str.len - 1; i >= 0; i--) + if (!trim_help_checkset(set, str.bytes[i])) + return i + 1; + return 0; +} + +static void trim_help_args(int32_t argc, Janet *argv, JanetByteView *str, JanetByteView *set) { + janet_arity(argc, 1, 2); + *str = janet_getbytes(argv, 0); + if (argc >= 2) { + *set = janet_getbytes(argv, 1); + } else { + set->bytes = (const uint8_t *)(" \t\r\n\v\f"); + set->len = 6; + } +} + +static Janet cfun_string_trim(int32_t argc, Janet *argv) { + JanetByteView str, set; + trim_help_args(argc, argv, &str, &set); + int32_t left_edge = trim_help_leftedge(str, set); + int32_t right_edge = trim_help_rightedge(str, set); + return janet_stringv(str.bytes + left_edge, right_edge - left_edge); +} + +static Janet cfun_string_triml(int32_t argc, Janet *argv) { + JanetByteView str, set; + trim_help_args(argc, argv, &str, &set); + int32_t left_edge = trim_help_leftedge(str, set); + return janet_stringv(str.bytes + left_edge, str.len - left_edge); +} + +static Janet cfun_string_trimr(int32_t argc, Janet *argv) { + JanetByteView str, set; + trim_help_args(argc, argv, &str, &set); + int32_t right_edge = trim_help_rightedge(str, set); + return janet_stringv(str.bytes, right_edge); +} + static const JanetReg string_cfuns[] = { { "string/slice", cfun_string_slice, @@ -574,6 +628,24 @@ static const JanetReg string_cfuns[] = { "Similar to snprintf, but specialized for operating with janet. Returns " "a new string.") }, + { + "string/trim", cfun_string_trim, + JDOC("(string/trim str [,set])\n\n" + "Trim leading and trailing whitespace from a byte sequence. If the argument " + "set is provided, consider only characters in set to be whitespace.") + }, + { + "string/triml", cfun_string_triml, + JDOC("(string/triml str [,set])\n\n" + "Trim leading whitespace from a byte sequence. If the argument " + "set is provided, consider only characters in set to be whitespace.") + }, + { + "string/trimr", cfun_string_trimr, + JDOC("(string/trimr str [,set])\n\n" + "Trim trailing whitespace from a byte sequence. If the argument " + "set is provided, consider only characters in set to be whitespace.") + }, {NULL, NULL, NULL} }; diff --git a/test/suite2.janet b/test/suite2.janet index c08b9baa..95937c1d 100644 --- a/test/suite2.janet +++ b/test/suite2.janet @@ -83,6 +83,16 @@ (assert (= (string/join @["one" "two" "three"] ", ") "one, two, three") "string/join 2") (assert (= (string/join @["one" "two" "three"]) "onetwothree") "string/join 3") (assert (= (string/join @[] "hi") "") "string/join 4") +(assert (= (string/trim " abcd ") "abcd") "string/trim 1") +(assert (= (string/trim "abcd \t\t\r\f") "abcd") "string/trim 2") +(assert (= (string/trim "\n\n\t abcd") "abcd") "string/trim 3") +(assert (= (string/trim "") "") "string/trim 4") +(assert (= (string/triml " abcd ") "abcd ") "string/triml 1") +(assert (= (string/triml "\tabcd \t\t\r\f") "abcd \t\t\r\f") "string/triml 2") +(assert (= (string/triml "abcd ") "abcd ") "string/triml 3") +(assert (= (string/trimr " abcd ") " abcd") "string/trimr 1") +(assert (= (string/trimr "\tabcd \t\t\r\f") "\tabcd") "string/trimr 2") +(assert (= (string/trimr " abcd") " abcd") "string/trimr 3") (assert (deep= (string/split "," "one,two,three") @["one" "two" "three"]) "string/split 1") (assert (deep= (string/split "," "onetwothree") @["onetwothree"]) "string/split 2") (assert (deep= (string/find-all "e" "onetwothree") @[2 9 10]) "string/find-all 1")