Improve documentation about MULE encoding.

This commit improves the comments in pg_wchar.h and creates #define symbols
for some formerly hard-coded values.  No substantive code changes.

Tatsuo Ishii and Tom Lane

diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c
index a266824b6bc555aaa6f7b29f5cdebbd94395fa6a..ed0e0c185cc6f17bac2df809159c8f4d5df6c06b 100644 (file)
--- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c
+++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c
@@ -168,7 +168,8 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len)
                    *p++ = LC_CNS11643_2;
                else
                {
-                   *p++ = 0x9d;    /* LCPRV2 */
+                   /* other planes are MULE private charsets */
+                   *p++ = LCPRV2_B;
                    *p++ = c1 - 0xa3 + LC_CNS11643_3;
                }
                *p++ = euc[2];
@@ -235,9 +236,9 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len)
            *p++ = mic[1];
            *p++ = mic[2];
        }
-       else if (c1 == 0x9d &&
+       else if (c1 == LCPRV2_B &&
                 mic[1] >= LC_CNS11643_3 && mic[1] <= LC_CNS11643_7)
-       {                       /* LCPRV2? */
+       {
            *p++ = SS2;
            *p++ = mic[1] - LC_CNS11643_3 + 0xa3;
            *p++ = mic[2];
@@ -286,10 +287,9 @@ big52mic(const unsigned char *big5, unsigned char *p, int len)
        cnsBuf = BIG5toCNS(big5buf, &lc);
        if (lc != 0)
        {
+           /* Planes 3 and 4 are MULE private charsets */
            if (lc == LC_CNS11643_3 || lc == LC_CNS11643_4)
-           {
-               *p++ = 0x9d;    /* LCPRV2 */
-           }
+               *p++ = LCPRV2_B;
            *p++ = lc;          /* Plane No. */
            *p++ = (cnsBuf >> 8) & 0x00ff;
            *p++ = cnsBuf & 0x00ff;
@@ -332,10 +332,9 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len)
        if (l < 0)
            report_invalid_encoding(PG_MULE_INTERNAL,
                                    (const char *) mic, len);
-       /* 0x9d means LCPRV2 */
-       if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == 0x9d)
+       if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == LCPRV2_B)
        {
-           if (c1 == 0x9d)
+           if (c1 == LCPRV2_B)
            {
                c1 = mic[1];    /* get plane no. */
                cnsBuf = (mic[2] << 8) | mic[3];

diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c
index 03d68119d1ce2fc482d4c00d7cb4b5448a2b8ed4..2e1db5ebf4b0071bfe1b57c8696eafff5ae31b2d 100644 (file)
--- a/src/backend/utils/mb/wchar.c
+++ b/src/backend/utils/mb/wchar.c
@@ -742,6 +742,12 @@ pg_mule_dsplen(const unsigned char *s)
 {
    int         len;
 
+   /*
+    * Note: it's not really appropriate to assume that all multibyte charsets
+    * are double-wide on screen.  But this seems an okay approximation for
+    * the MULE charsets we currently support.
+    */
+
    if (IS_LC1(*s))
        len = 1;
    else if (IS_LCPRV1(*s))

diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h
index d456309486cfc356310252d0f4fcc4cb864676ed..1d6d9554bd4ca57176bbcf54879246b07b281118 100644 (file)
--- a/src/include/mb/pg_wchar.h
+++ b/src/include/mb/pg_wchar.h
@@ -36,36 +36,60 @@ typedef unsigned int pg_wchar;
 #define ISSJISHEAD(c) (((c) >= 0x81 && (c) <= 0x9f) || ((c) >= 0xe0 && (c) <= 0xfc))
 #define ISSJISTAIL(c) (((c) >= 0x40 && (c) <= 0x7e) || ((c) >= 0x80 && (c) <= 0xfc))
 
-/*
- * Leading byte types or leading prefix byte for MULE internal code.
- * See http://www.xemacs.org for more details. (there is a doc titled
- * "XEmacs Internals Manual", "MULE Character Sets and Encodings"
- * section.)
- */
-/*
- * Is a leading byte for "official" single byte encodings?
- */
-#define IS_LC1(c)  ((unsigned char)(c) >= 0x81 && (unsigned char)(c) <= 0x8d)
-/*
- * Is a prefix byte for "private" single byte encodings?
- */
-#define IS_LCPRV1(c)   ((unsigned char)(c) == 0x9a || (unsigned char)(c) == 0x9b)
-/*
- * Is a leading byte for "official" multibyte encodings?
- */
-#define IS_LC2(c)  ((unsigned char)(c) >= 0x90 && (unsigned char)(c) <= 0x99)
-/*
- * Is a prefix byte for "private" multibyte encodings?
- */
-#define IS_LCPRV2(c)   ((unsigned char)(c) == 0x9c || (unsigned char)(c) == 0x9d)
-
 /*----------------------------------------------------
- * leading characters
+ * MULE Internal Encoding (MIC)
+ *
+ * This encoding follows the design used within XEmacs; it is meant to
+ * subsume many externally-defined character sets.  Each character includes
+ * identification of the character set it belongs to, so the encoding is
+ * general but somewhat bulky.
+ *
+ * Currently PostgreSQL supports 5 types of MULE character sets:
+ *
+ * 1) 1-byte ASCII characters.  Each byte is below 0x80.
+ *
+ * 2) "Official" single byte charsets such as ISO-8859-1 (Latin1).
+ *    Each MULE character consists of 2 bytes: LC1 + C1, where LC1 is
+ *    an identifier for the charset (in the range 0x81 to 0x8d) and C1
+ *    is the character code (in the range 0xa0 to 0xff).
+ *
+ * 3) "Private" single byte charsets such as SISHENG.  Each MULE
+ *    character consists of 3 bytes: LCPRV1 + LC12 + C1, where LCPRV1
+ *    is a private-charset flag, LC12 is an identifier for the charset,
+ *    and C1 is the character code (in the range 0xa0 to 0xff).
+ *    LCPRV1 is either 0x9a (if LC12 is in the range 0xa0 to 0xdf)
+ *    or 0x9b (if LC12 is in the range 0xe0 to 0xef).
+ *
+ * 4) "Official" multibyte charsets such as JIS X0208.  Each MULE
+ *    character consists of 3 bytes: LC2 + C1 + C2, where LC2 is
+ *    an identifier for the charset (in the range 0x90 to 0x99) and C1
+ *    and C2 form the character code (each in the range 0xa0 to 0xff).
+ *
+ * 5) "Private" multibyte charsets such as CNS 11643-1992 Plane 3.
+ *    Each MULE character consists of 4 bytes: LCPRV2 + LC22 + C1 + C2,
+ *    where LCPRV2 is a private-charset flag, LC22 is an identifier for
+ *    the charset, and C1 and C2 form the character code (each in the range
+ *    0xa0 to 0xff).  LCPRV2 is either 0x9c (if LC22 is in the range 0xf0
+ *    to 0xf4) or 0x9d (if LC22 is in the range 0xf5 to 0xfe).
+ *
+ * "Official" encodings are those that have been assigned code numbers by
+ * the XEmacs project; "private" encodings have Postgres-specific charset
+ * identifiers.
+ *
+ * See the "XEmacs Internals Manual", available at http://www.xemacs.org,
+ * for more details.  Note that for historical reasons, Postgres'
+ * private-charset flag values do not match what XEmacs says they should be,
+ * so this isn't really exactly MULE (not that private charsets would be
+ * interoperable anyway).
  *----------------------------------------------------
  */
 
 /*
- * Official single byte encodings (0x81-0x8e)
+ * Charset identifiers (also called "leading bytes" in the MULE documentation)
+ */
+
+/*
+ * Charset IDs for official single byte encodings (0x81-0x8e)
  */
 #define LC_ISO8859_1       0x81    /* ISO8859 Latin 1 */
 #define LC_ISO8859_2       0x82    /* ISO8859 Latin 2 */
@@ -79,21 +103,19 @@ typedef unsigned int pg_wchar;
 #define LC_JISX0201R       0x8a    /* Japanese 1 byte Roman */
 /* Note that 0x8b seems to be unused as of Emacs 20.7.
  * However, there might be a chance that 0x8b could be used
- * in later version of Emacs.
+ * in later versions of Emacs.
  */
 #define LC_KOI8_R          0x8b    /* Cyrillic KOI8-R */
-#define LC_KOI8_U          0x8b    /* Cyrillic KOI8-U */
 #define LC_ISO8859_5       0x8c    /* ISO8859 Cyrillic */
 #define LC_ISO8859_9       0x8d    /* ISO8859 Latin 5 (not supported yet) */
 /* #define FREE                0x8e    free (unused) */
+/* #define CONTROL_1       0x8f    control characters (unused) */
 
-/*
- * Unused
- */
-#define CONTROL_1          0x8f    /* control characters (unused) */
+/* Is a leading byte for "official" single byte encodings? */
+#define IS_LC1(c)  ((unsigned char)(c) >= 0x81 && (unsigned char)(c) <= 0x8d)
 
 /*
- * Official multibyte byte encodings (0x90-0x99)
+ * Charset IDs for official multibyte encodings (0x90-0x99)
  * 0x9a-0x9d are free. 0x9e and 0x9f are reserved.
  */
 #define LC_JISX0208_1978   0x90    /* Japanese Kanji, old JIS (not supported) */
@@ -108,45 +130,70 @@ typedef unsigned int pg_wchar;
 #define LC_BIG5_1          0x98    /* Plane 1 Chinese traditional (not supported) */
 #define LC_BIG5_2          0x99    /* Plane 1 Chinese traditional (not supported) */
 
+/* Is a leading byte for "official" multibyte encodings? */
+#define IS_LC2(c)  ((unsigned char)(c) >= 0x90 && (unsigned char)(c) <= 0x99)
+
 /*
- * Private single byte encodings (0xa0-0xef)
+ * Postgres-specific prefix bytes for "private" single byte encodings
+ * (According to the MULE docs, we should be using 0x9e for this)
  */
-#define LC_SISHENG         0xa0/* Chinese SiSheng characters for
-                                * PinYin/ZhuYin (not supported) */
-#define LC_IPA             0xa1/* IPA (International Phonetic Association)
-                                * (not supported) */
-#define LC_VISCII_LOWER        0xa2/* Vietnamese VISCII1.1 lower-case (not
-                                * supported) */
-#define LC_VISCII_UPPER        0xa3/* Vietnamese VISCII1.1 upper-case (not
-                                * supported) */
+#define LCPRV1_A       0x9a
+#define LCPRV1_B       0x9b
+#define IS_LCPRV1(c)   ((unsigned char)(c) == LCPRV1_A || (unsigned char)(c) == LCPRV1_B)
+
+/*
+ * Postgres-specific prefix bytes for "private" multibyte encodings
+ * (According to the MULE docs, we should be using 0x9f for this)
+ */
+#define LCPRV2_A       0x9c
+#define LCPRV2_B       0x9d
+#define IS_LCPRV2(c)   ((unsigned char)(c) == LCPRV2_A || (unsigned char)(c) == LCPRV2_B)
+
+/*
+ * Charset IDs for private single byte encodings (0xa0-0xef)
+ */
+#define LC_SISHENG         0xa0    /* Chinese SiSheng characters for
+                                    * PinYin/ZhuYin (not supported) */
+#define LC_IPA             0xa1    /* IPA (International Phonetic Association)
+                                    * (not supported) */
+#define LC_VISCII_LOWER        0xa2    /* Vietnamese VISCII1.1 lower-case (not
+                                    * supported) */
+#define LC_VISCII_UPPER        0xa3    /* Vietnamese VISCII1.1 upper-case (not
+                                    * supported) */
 #define LC_ARABIC_DIGIT        0xa4    /* Arabic digit (not supported) */
 #define LC_ARABIC_1_COLUMN 0xa5    /* Arabic 1-column (not supported) */
 #define LC_ASCII_RIGHT_TO_LEFT 0xa6    /* ASCII (left half of ISO8859-1) with
                                         * right-to-left direction (not
                                         * supported) */
-#define LC_LAO             0xa7/* Lao characters (ISO10646 0E80..0EDF) (not
-                                * supported) */
+#define LC_LAO             0xa7    /* Lao characters (ISO10646 0E80..0EDF)
+                                    * (not supported) */
 #define LC_ARABIC_2_COLUMN 0xa8    /* Arabic 1-column (not supported) */
 
 /*
- * Private multibyte encodings (0xf0-0xff)
+ * Charset IDs for private multibyte encodings (0xf0-0xff)
  */
-#define LC_INDIAN_1_COLUMN 0xf0/* Indian charset for 1-column width glypps
-                                * (not supported) */
-#define LC_TIBETAN_1_COLUMN 0xf1   /* Tibetan 1 column glyph (not supported) */
+#define LC_INDIAN_1_COLUMN 0xf0    /* Indian charset for 1-column width glyphs
+                                    * (not supported) */
+#define LC_TIBETAN_1_COLUMN 0xf1   /* Tibetan 1-column width glyphs
+                                    * (not supported) */
 #define LC_ETHIOPIC            0xf5    /* Ethiopic characters (not supported) */
 #define LC_CNS11643_3      0xf6    /* CNS 11643-1992 Plane 3 */
 #define LC_CNS11643_4      0xf7    /* CNS 11643-1992 Plane 4 */
 #define LC_CNS11643_5      0xf8    /* CNS 11643-1992 Plane 5 */
 #define LC_CNS11643_6      0xf9    /* CNS 11643-1992 Plane 6 */
 #define LC_CNS11643_7      0xfa    /* CNS 11643-1992 Plane 7 */
-#define LC_INDIAN_2_COLUMN 0xfb/* Indian charset for 2-column width glypps
-                                * (not supported) */
+#define LC_INDIAN_2_COLUMN 0xfb    /* Indian charset for 2-column width glyphs
+                                    * (not supported) */
 #define LC_TIBETAN         0xfc    /* Tibetan (not supported) */
 /* #define FREE                0xfd    free (unused) */
 /* #define FREE                0xfe    free (unused) */
 /* #define FREE                0xff    free (unused) */
 
+/*----------------------------------------------------
+ * end of MULE stuff
+ *----------------------------------------------------
+ */
+
 /*
  * PostgreSQL encoding identifiers
  *