[systemd-devel] [PATCH] util, utf8: new wellipsize and wellipsize_mem that take into account multi-byte characters

Shawn Landden shawn at churchofgit.com
Wed Aug 28 15:17:17 PDT 2013


This version counts all multibyte characters as 1 width, not taking into
account double width cjk characters and zerowidth characters
---
 TODO              |  4 ---
 src/shared/utf8.c | 56 +++++++++++++++++++++++++++++++
 src/shared/utf8.h | 98 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 src/shared/util.c | 55 +++++++++++++++++++++++++++++++
 src/shared/util.h |  2 ++
 5 files changed, 211 insertions(+), 4 deletions(-)

diff --git a/TODO b/TODO
index fe305ec..a77ebe5 100644
--- a/TODO
+++ b/TODO
@@ -19,10 +19,6 @@ Bugfixes:
 
 * properly handle .mount unit state tracking when two mount points are stacked one on top of another on the exact same mount point.
 
-* ellipsize_mem must take into account multi-byte unicode characters, and
-  - make the resulting line the requested number of *characters*, not *bytes*,
-  - avoid truncuating multi-byte sequences in the middle.
-
 * When we detect invalid UTF-8, we cant't use it in an error message:
   log...("Path is not UTF-8 clean, ignoring assignment: %s", rvalue);
 
diff --git a/src/shared/utf8.c b/src/shared/utf8.c
index 655cc77..8a37c3a 100644
--- a/src/shared/utf8.c
+++ b/src/shared/utf8.c
@@ -22,6 +22,11 @@
 /* This file is based on the GLIB utf8 validation functions. The
  * original license text follows. */
 
+/* gunicode.h - Unicode manipulation functions
+ *
+ *  Copyright (C) 1999, 2000 Tom Tromey
+ *  Copyright 2000, 2005 Red Hat, Inc.
+ */
 /* gutf8.c - Operations on UTF-8 strings.
  *
  * Copyright (C) 1999 Tom Tromey
@@ -317,3 +322,54 @@ char *utf16_to_utf8(const void *s, size_t length) {
 
         return r;
 }
+
+/**
+ * g_utf8_prev_char:
+ * @p: a pointer to a position within a UTF-8 encoded string
+ *
+ * Finds the previous UTF-8 character in the string before @p.
+ *
+ * @p does not have to be at the beginning of a UTF-8 character. No check
+ * is made to see if the character found is actually valid other than
+ * it starts with an appropriate byte. If @p might be the first
+ * character of the string, you must use g_utf8_find_prev_char() instead.
+ *
+ * Return value: a pointer to the found character.
+ **/
+char *
+utf8_prev_char (const char *p)
+{
+  while (1)
+    {
+      p--;
+      if ((*p & 0xc0) != 0x80)
+	return (char *)p;
+    }
+}
+
+/**
+ * g_utf8_get_char:
+ * @p: a pointer to Unicode character encoded as UTF-8
+ *
+ * Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
+ * If @p does not point to a valid UTF-8 encoded character, results are
+ * undefined. If you are not sure that the bytes are complete
+ * valid Unicode characters, you should use g_utf8_get_char_validated()
+ * instead.
+ *
+ * Return value: the resulting character
+ **/
+unichar
+utf8_get_char (const char *p)
+{
+  int i, mask = 0, len;
+  unichar result;
+  unsigned char c = (unsigned char) *p;
+
+  UTF8_COMPUTE (c, mask, len);
+  if (len == -1)
+    return (unichar)-1;
+  UTF8_GET (result, p, i, mask, len);
+
+  return result;
+}
\ No newline at end of file
diff --git a/src/shared/utf8.h b/src/shared/utf8.h
index f805ea6..020bc27 100644
--- a/src/shared/utf8.h
+++ b/src/shared/utf8.h
@@ -34,3 +34,101 @@ char *utf8_filter(const char *s);
 char *ascii_filter(const char *s);
 
 char *utf16_to_utf8(const void *s, size_t length);
+
+#define unichar uint32_t
+
+char *utf8_prev_char (const char *p);
+unichar utf8_get_char (const char *p);
+
+#define UTF8_COMPUTE(Char, Mask, Len)					      \
+  if (Char < 128)							      \
+    {									      \
+      Len = 1;								      \
+      Mask = 0x7f;							      \
+    }									      \
+  else if ((Char & 0xe0) == 0xc0)					      \
+    {									      \
+      Len = 2;								      \
+      Mask = 0x1f;							      \
+    }									      \
+  else if ((Char & 0xf0) == 0xe0)					      \
+    {									      \
+      Len = 3;								      \
+      Mask = 0x0f;							      \
+    }									      \
+  else if ((Char & 0xf8) == 0xf0)					      \
+    {									      \
+      Len = 4;								      \
+      Mask = 0x07;							      \
+    }									      \
+  else if ((Char & 0xfc) == 0xf8)					      \
+    {									      \
+      Len = 5;								      \
+      Mask = 0x03;							      \
+    }									      \
+  else if ((Char & 0xfe) == 0xfc)					      \
+    {									      \
+      Len = 6;								      \
+      Mask = 0x01;							      \
+    }									      \
+  else									      \
+    Len = -1;
+
+#define UTF8_LENGTH(Char)              \
+  ((Char) < 0x80 ? 1 :                 \
+   ((Char) < 0x800 ? 2 :               \
+    ((Char) < 0x10000 ? 3 :            \
+     ((Char) < 0x200000 ? 4 :          \
+      ((Char) < 0x4000000 ? 5 : 6)))))
+
+
+#define UTF8_GET(Result, Chars, Count, Mask, Len)			      \
+  (Result) = (Chars)[0] & (Mask);					      \
+  for ((Count) = 1; (Count) < (Len); ++(Count))				      \
+    {									      \
+      if (((Chars)[(Count)] & 0xc0) != 0x80)				      \
+	{								      \
+	  (Result) = -1;						      \
+	  break;							      \
+	}								      \
+      (Result) <<= 6;							      \
+      (Result) |= ((Chars)[(Count)] & 0x3f);				      \
+    }
+
+/*
+ * Check whether a Unicode (5.2) char is in a valid range.
+ *
+ * The first check comes from the Unicode guarantee to never encode
+ * a point above 0x0010ffff, since UTF-16 couldn't represent it.
+ *
+ * The second check covers surrogate pairs (category Cs).
+ *
+ * @param Char the character
+ */
+#define UNICODE_VALID(Char)                   \
+    ((Char) < 0x110000 &&                     \
+     (((Char) & 0xFFFFF800) != 0xD800))
+
+static const char utf8_skip_data[256] = {
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+  3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
+};
+
+/**
+ * g_utf8_next_char:
+ * @p: Pointer to the start of a valid UTF-8 character
+ *
+ * Skips to the next character in a UTF-8 string. The string must be
+ * valid; this macro is as fast as possible, and has no error-checking.
+ * You would use this macro to iterate over a string character by
+ * character. The macro returns the start of the next UTF-8 character.
+ * Before using this macro, use g_utf8_validate() to validate strings
+ * that may contain invalid UTF-8.
+ */
+#define utf8_next_char(p) (char *)((p) + utf8_skip_data[*(const char *)(p)])
\ No newline at end of file
diff --git a/src/shared/util.c b/src/shared/util.c
index 9af99aa..58a1787 100644
--- a/src/shared/util.c
+++ b/src/shared/util.c
@@ -73,6 +73,7 @@
 #include "hashmap.h"
 #include "env-util.h"
 #include "fileio.h"
+#include "utf8.h"
 
 int saved_argc = 0;
 char **saved_argv = NULL;
@@ -3327,6 +3328,60 @@ char *ellipsize(const char *s, size_t length, unsigned percent) {
         return ellipsize_mem(s, strlen(s), length, percent);
 }
 
+char *wellipsize_mem(const char *s, size_t old_length, size_t new_length, unsigned percent) {
+        size_t x;
+        char *e, *i;
+        unichar c;
+        unsigned j, k = 0;
+
+        assert(s);
+        assert(percent <= 100);
+        assert(new_length >= 3);
+
+        /* if no multibyte characters use ellipsize_mem for speed */
+        if (ascii_is_valid(s))
+                return ellipsize_mem(s, old_length, new_length, percent);
+
+        if (old_length <= 3 || old_length <= new_length)
+                return strndup(s, old_length);
+
+        if (!utf8_is_valid(s))
+                return NULL;
+
+        e = new0(char, new_length*4 < old_length ? new_length*4 : old_length);
+        if (!e)
+                return NULL;
+
+        x = (new_length * percent) / 100;
+
+        if (x > new_length - 3)
+                x = new_length - 3;
+
+        for (i = (char *)s;k < x;i = utf8_next_char(i))
+                k++;
+
+        j = i - s;
+        memcpy(e, s, j);
+        e[j] = '.';   /* TODO: use … tri-dot? */
+        e[j+1] = '.'; /* 0xe2 0x80 0xa6 */
+        e[j+2] = '.';
+
+        k = 0;
+        for (i = (char *)s + old_length;
+             k < new_length - x - 3;) {
+                i = utf8_prev_char(i);
+                k++;
+        }
+
+        strcpy(e + j + 3, i);
+
+        return e;
+}
+
+char *wellipsize(const char *s, size_t length, unsigned percent) {
+        return wellipsize_mem(s, strlen(s), length, percent);
+}
+
 int touch(const char *path) {
         int fd;
 
diff --git a/src/shared/util.h b/src/shared/util.h
index 63f4e3d..9b17db9 100644
--- a/src/shared/util.h
+++ b/src/shared/util.h
@@ -404,6 +404,8 @@ int running_in_chroot(void);
 
 char *ellipsize(const char *s, size_t length, unsigned percent);
 char *ellipsize_mem(const char *s, size_t old_length, size_t new_length, unsigned percent);
+char *wellipsize(const char *s, size_t length, unsigned percent);
+char *wellipsize_mem(const char *s, size_t old_length, size_t new_length, unsigned percent);
 
 int touch(const char *path);
 
-- 
1.8.4.rc3



More information about the systemd-devel mailing list