From e4e84f0147a1ebd588eb29959af7773527857912 Mon Sep 17 00:00:00 2001
From: Al <albarrentine@gmail.com>
Date: Fri, 8 Dec 2017 14:28:30 -0500
Subject: [PATCH] [utils] adding unicode_common_prefix/unicode_common_suffix,
 string_hyphen_prefix_len and string_hyphen_suffix_len to string_utils

---
 src/string_utils.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++
 src/string_utils.h |  5 ++++
 2 files changed, 68 insertions(+)

diff --git a/src/string_utils.c b/src/string_utils.c
index 567c2213..7045dd25 100644
--- a/src/string_utils.c
+++ b/src/string_utils.c
@@ -410,6 +410,47 @@ bool unicode_equals(uint32_array *u1_array, uint32_array *u2_array) {
     return true;
 }
 
+size_t unicode_common_prefix(uint32_array *u1_array, uint32_array *u2_array) {
+    size_t len1 = u1_array->n;
+    size_t len2 = u2_array->n;
+
+    size_t min_len = len1 <= len2 ? len1 : len2;
+
+    uint32_t *u1 = u1_array->a;
+    uint32_t *u2 = u2_array->a;
+    size_t common_prefix = 0;
+
+    for (size_t i = 0; i < min_len; i++) {
+        if (u1[i] == u2[i]) {
+            common_prefix++;
+        } else {
+            break;
+        }
+    }
+    return common_prefix;
+}
+
+size_t unicode_common_suffix(uint32_array *u1_array, uint32_array *u2_array) {
+    size_t len1 = u1_array->n;
+    size_t len2 = u2_array->n;
+
+    size_t min_len = len1 <= len2 ? len1 : len2;
+
+    uint32_t *u1 = u1_array->a;
+    uint32_t *u2 = u2_array->a;
+    size_t common_suffix = 0;
+
+    for (size_t i = 0; i < min_len; i++) {
+        if (u1[len1 - i - 1] == u2[len2 - i - 1]) {
+            common_suffix++;
+        } else {
+            break;
+        }
+    }
+    return common_suffix;
+}
+
+
 
 int utf8_compare_len(const char *str1, const char *str2, size_t len) {
     if (len == 0) return 0;
@@ -749,6 +790,28 @@ size_t string_right_spaces_len(char *str, size_t len) {
 
 }
 
+inline size_t string_hyphen_prefix_len(char *str, size_t len) {
+    // Strip beginning hyphens
+    int32_t unichr;
+    uint8_t *ptr = (uint8_t *)str;
+    ssize_t char_len = utf8proc_iterate(ptr, len, &unichr);
+    if (utf8_is_hyphen(unichr)) {
+        return (size_t)char_len;
+    }
+    return 0;
+}
+
+inline size_t string_hyphen_suffix_len(char *str, size_t len) {
+    // Strip ending hyphens
+    int32_t unichr;
+    uint8_t *ptr = (uint8_t *)str;
+    ssize_t char_len = utf8proc_iterate_reversed(ptr, len, &unichr);
+    if (utf8_is_hyphen(unichr)) {
+        return (size_t)char_len;
+    }
+    return 0;
+}
+
 size_t string_left_spaces_len(char *str, size_t len) {
     size_t spaces = 0;
 
diff --git a/src/string_utils.h b/src/string_utils.h
index 86a018d8..a94f1d93 100644
--- a/src/string_utils.h
+++ b/src/string_utils.h
@@ -89,6 +89,8 @@ ssize_t utf8_len(const char *str, size_t len);
 
 uint32_array *unicode_codepoints(const char *str);
 bool unicode_equals(uint32_array *u1_array, uint32_array *u2_array);
+size_t unicode_common_prefix(uint32_array *u1_array, uint32_array *u2_array);
+size_t unicode_common_suffix(uint32_array *u1_array, uint32_array *u2_array);
 
 bool utf8_is_hyphen(int32_t ch);
 bool utf8_is_period(int32_t ch);
@@ -119,6 +121,9 @@ bool string_contains_period(char *str);
 
 char *string_trim(char *str);
 
+size_t string_hyphen_prefix_len(char *str, size_t len);
+size_t string_hyphen_suffix_len(char *str, size_t len);
+
 /* char_array is a dynamic character array defined in collections.h
 but has a few additional methods related to string manipulation.