[Python-checkins] cpython: CJK codecs: less magical macros, semicolon is now explicit
victor.stinner
python-checkins at python.org
Tue Oct 29 01:02:29 CET 2013
http://hg.python.org/cpython/rev/6b86eb127030
changeset: 86714:6b86eb127030
user: Victor Stinner <victor.stinner at gmail.com>
date: Tue Oct 29 00:59:44 2013 +0100
summary:
CJK codecs: less magical macros, semicolon is now explicit
files:
Modules/cjkcodecs/_codecs_cn.c | 27 +-
Modules/cjkcodecs/_codecs_hk.c | 2 +-
Modules/cjkcodecs/_codecs_iso2022.c | 138 +++++++------
Modules/cjkcodecs/_codecs_jp.c | 21 +-
Modules/cjkcodecs/_codecs_kr.c | 15 +-
Modules/cjkcodecs/_codecs_tw.c | 4 +-
Modules/cjkcodecs/cjkcodecs.h | 7 +-
Modules/cjkcodecs/emu_jisx0213_2000.h | 2 +-
8 files changed, 115 insertions(+), 101 deletions(-)
diff --git a/Modules/cjkcodecs/_codecs_cn.c b/Modules/cjkcodecs/_codecs_cn.c
--- a/Modules/cjkcodecs/_codecs_cn.c
+++ b/Modules/cjkcodecs/_codecs_cn.c
@@ -40,14 +40,15 @@
OUTCHAR(decoded); \
}
-#define GBK_ENCODE(code, assi) \
- if ((code) == 0x2014) { \
- (assi) = 0xa1aa; \
- } else if ((code) == 0x2015) { \
- (assi) = 0xa844; \
- } else if ((code) == 0x00b7) { \
- (assi) = 0xa1a4; \
+#define GBK_ENCODE(code, assi) \
+ if ((code) == 0x2014) { \
+ (assi) = 0xa1aa; \
+ } else if ((code) == 0x2015) { \
+ (assi) = 0xa844; \
+ } else if ((code) == 0x00b7) { \
+ (assi) = 0xa1a4; \
} else if ((code) != 0x30fb && TRYMAP_ENC(gbcommon, assi, code)) { \
+ ; \
}
/*
@@ -98,7 +99,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (TRYMAP_DEC(gb2312, decoded, c ^ 0x80, INBYTE2 ^ 0x80)) {
OUTCHAR(decoded);
NEXT_IN(2);
@@ -159,7 +160,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
GBK_DECODE(c, INBYTE2, writer)
else
@@ -267,7 +268,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (c2 >= 0x30 && c2 <= 0x39) { /* 4 bytes seq */
@@ -275,7 +276,7 @@
unsigned char c3, c4;
Py_UCS4 lseq;
- REQUIRE_INBUF(4)
+ REQUIRE_INBUF(4);
c3 = INBYTE3;
c4 = INBYTE4;
if (c < 0x81 || c3 < 0x81 || c4 < 0x30 || c4 > 0x39)
@@ -405,7 +406,7 @@
if (c == '~') {
unsigned char c2 = INBYTE2;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (c2 == '~') {
OUTCHAR('~');
NEXT_IN(2);
@@ -431,7 +432,7 @@
NEXT_IN(1);
}
else { /* GB mode */
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (TRYMAP_DEC(gb2312, decoded, c, INBYTE2)) {
OUTCHAR(decoded);
NEXT_IN(2);
diff --git a/Modules/cjkcodecs/_codecs_hk.c b/Modules/cjkcodecs/_codecs_hk.c
--- a/Modules/cjkcodecs/_codecs_hk.c
+++ b/Modules/cjkcodecs/_codecs_hk.c
@@ -119,7 +119,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (0xc6 > c || c > 0xc8 || (c < 0xc7 && INBYTE2 < 0xa1)) {
if (TRYMAP_DEC(big5, decoded, c, INBYTE2)) {
diff --git a/Modules/cjkcodecs/_codecs_iso2022.c b/Modules/cjkcodecs/_codecs_iso2022.c
--- a/Modules/cjkcodecs/_codecs_iso2022.c
+++ b/Modules/cjkcodecs/_codecs_iso2022.c
@@ -73,7 +73,7 @@
#define F_SHIFTED 0x01
#define F_ESCTHROUGHOUT 0x02
-#define STATE_SETG(dn, v) ((state)->c[dn]) = (v);
+#define STATE_SETG(dn, v) do { ((state)->c[dn]) = (v); } while (0)
#define STATE_GETG(dn) ((state)->c[dn])
#define STATE_G0 STATE_GETG(0)
@@ -85,10 +85,10 @@
#define STATE_SETG2(v) STATE_SETG(2, v)
#define STATE_SETG3(v) STATE_SETG(3, v)
-#define STATE_SETFLAG(f) ((state)->c[4]) |= (f);
+#define STATE_SETFLAG(f) do { ((state)->c[4]) |= (f); } while (0)
#define STATE_GETFLAG(f) ((state)->c[4] & (f))
-#define STATE_CLEARFLAG(f) ((state)->c[4]) &= ~(f);
-#define STATE_CLEARFLAGS() ((state)->c[4]) = 0;
+#define STATE_CLEARFLAG(f) do { ((state)->c[4]) &= ~(f); } while (0)
+#define STATE_CLEARFLAGS() do { ((state)->c[4]) = 0; } while (0)
#define ISO2022_CONFIG ((const struct iso2022_config *)config)
#define CONFIG_ISSET(flag) (ISO2022_CONFIG->flags & (flag))
@@ -132,9 +132,9 @@
ENCODER_INIT(iso2022)
{
- STATE_CLEARFLAGS()
- STATE_SETG0(CHARSET_ASCII)
- STATE_SETG1(CHARSET_ASCII)
+ STATE_CLEARFLAGS();
+ STATE_SETG0(CHARSET_ASCII);
+ STATE_SETG1(CHARSET_ASCII);
return 0;
}
@@ -143,12 +143,12 @@
if (STATE_GETFLAG(F_SHIFTED)) {
WRITEBYTE1(SI);
NEXT_OUT(1);
- STATE_CLEARFLAG(F_SHIFTED)
+ STATE_CLEARFLAG(F_SHIFTED);
}
if (STATE_G0 != CHARSET_ASCII) {
WRITEBYTE3(ESC, '(', 'B');
NEXT_OUT(3);
- STATE_SETG0(CHARSET_ASCII)
+ STATE_SETG0(CHARSET_ASCII);
}
return 0;
}
@@ -164,12 +164,12 @@
if (c < 0x80) {
if (STATE_G0 != CHARSET_ASCII) {
WRITEBYTE3(ESC, '(', 'B');
- STATE_SETG0(CHARSET_ASCII)
+ STATE_SETG0(CHARSET_ASCII);
NEXT_OUT(3);
}
if (STATE_GETFLAG(F_SHIFTED)) {
WRITEBYTE1(SI);
- STATE_CLEARFLAG(F_SHIFTED)
+ STATE_CLEARFLAG(F_SHIFTED);
NEXT_OUT(1);
}
WRITEBYTE1((unsigned char)c);
@@ -211,24 +211,24 @@
case 0: /* G0 */
if (STATE_GETFLAG(F_SHIFTED)) {
WRITEBYTE1(SI);
- STATE_CLEARFLAG(F_SHIFTED)
+ STATE_CLEARFLAG(F_SHIFTED);
NEXT_OUT(1);
}
if (STATE_G0 != dsg->mark) {
if (dsg->width == 1) {
WRITEBYTE3(ESC, '(', ESCMARK(dsg->mark));
- STATE_SETG0(dsg->mark)
+ STATE_SETG0(dsg->mark);
NEXT_OUT(3);
}
else if (dsg->mark == CHARSET_JISX0208) {
WRITEBYTE3(ESC, '$', ESCMARK(dsg->mark));
- STATE_SETG0(dsg->mark)
+ STATE_SETG0(dsg->mark);
NEXT_OUT(3);
}
else {
WRITEBYTE4(ESC, '$', '(',
ESCMARK(dsg->mark));
- STATE_SETG0(dsg->mark)
+ STATE_SETG0(dsg->mark);
NEXT_OUT(4);
}
}
@@ -237,19 +237,18 @@
if (STATE_G1 != dsg->mark) {
if (dsg->width == 1) {
WRITEBYTE3(ESC, ')', ESCMARK(dsg->mark));
- STATE_SETG1(dsg->mark)
+ STATE_SETG1(dsg->mark);
NEXT_OUT(3);
}
else {
- WRITEBYTE4(ESC, '$', ')',
- ESCMARK(dsg->mark));
- STATE_SETG1(dsg->mark)
+ WRITEBYTE4(ESC, '$', ')', ESCMARK(dsg->mark));
+ STATE_SETG1(dsg->mark);
NEXT_OUT(4);
}
}
if (!STATE_GETFLAG(F_SHIFTED)) {
WRITEBYTE1(SO);
- STATE_SETFLAG(F_SHIFTED)
+ STATE_SETFLAG(F_SHIFTED);
NEXT_OUT(1);
}
break;
@@ -274,17 +273,17 @@
DECODER_INIT(iso2022)
{
- STATE_CLEARFLAGS()
- STATE_SETG0(CHARSET_ASCII)
- STATE_SETG1(CHARSET_ASCII)
- STATE_SETG2(CHARSET_ASCII)
+ STATE_CLEARFLAGS();
+ STATE_SETG0(CHARSET_ASCII);
+ STATE_SETG1(CHARSET_ASCII);
+ STATE_SETG2(CHARSET_ASCII);
return 0;
}
DECODER_RESET(iso2022)
{
- STATE_SETG0(CHARSET_ASCII)
- STATE_CLEARFLAG(F_SHIFTED)
+ STATE_SETG0(CHARSET_ASCII);
+ STATE_CLEARFLAG(F_SHIFTED);
return 0;
}
@@ -303,8 +302,9 @@
break;
}
else if (CONFIG_ISSET(USE_JISX0208_EXT) && i+1 < *inleft &&
- (*inbuf)[i] == '&' && (*inbuf)[i+1] == '@')
+ (*inbuf)[i] == '&' && (*inbuf)[i+1] == '@') {
i += 2;
+ }
}
if (i >= MAX_ESCSEQLEN)
@@ -358,14 +358,15 @@
if (charset != CHARSET_ASCII) {
const struct iso2022_designation *dsg;
- for (dsg = CONFIG_DESIGNATIONS; dsg->mark; dsg++)
+ for (dsg = CONFIG_DESIGNATIONS; dsg->mark; dsg++) {
if (dsg->mark == charset)
break;
+ }
if (!dsg->mark)
return esclen;
}
- STATE_SETG(designation, charset)
+ STATE_SETG(designation, charset);
*inleft -= esclen;
(*inbuf) += esclen;
return 0;
@@ -433,14 +434,14 @@
OUTCHAR(c); /* assume as ISO-8859-1 */
NEXT_IN(1);
if (IS_ESCEND(c)) {
- STATE_CLEARFLAG(F_ESCTHROUGHOUT)
+ STATE_CLEARFLAG(F_ESCTHROUGHOUT);
}
continue;
}
switch (c) {
case ESC:
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (IS_ISO2022ESC(INBYTE2)) {
err = iso2022processesc(config, state,
inbuf, &inleft);
@@ -448,7 +449,7 @@
return err;
}
else if (CONFIG_ISSET(USE_G2) && INBYTE2 == 'N') {/* SS2 */
- REQUIRE_INBUF(3)
+ REQUIRE_INBUF(3);
err = iso2022processg2(config, state,
inbuf, &inleft, writer);
if (err != 0)
@@ -456,24 +457,24 @@
}
else {
OUTCHAR(ESC);
- STATE_SETFLAG(F_ESCTHROUGHOUT)
+ STATE_SETFLAG(F_ESCTHROUGHOUT);
NEXT_IN(1);
}
break;
case SI:
if (CONFIG_ISSET(NO_SHIFT))
goto bypass;
- STATE_CLEARFLAG(F_SHIFTED)
+ STATE_CLEARFLAG(F_SHIFTED);
NEXT_IN(1);
break;
case SO:
if (CONFIG_ISSET(NO_SHIFT))
goto bypass;
- STATE_SETFLAG(F_SHIFTED)
+ STATE_SETFLAG(F_SHIFTED);
NEXT_IN(1);
break;
case LF:
- STATE_CLEARFLAG(F_SHIFTED)
+ STATE_CLEARFLAG(F_SHIFTED);
OUTCHAR(LF);
NEXT_IN(1);
break;
@@ -493,38 +494,41 @@
charset = STATE_G0;
if (charset == CHARSET_ASCII) {
-bypass: OUTCHAR(c);
- NEXT_IN(1);
- break;
- }
+bypass:
+ OUTCHAR(c);
+ NEXT_IN(1);
+ break;
+ }
- if (dsgcache != NULL &&
- dsgcache->mark == charset)
- dsg = dsgcache;
- else {
- for (dsg = CONFIG_DESIGNATIONS;
- dsg->mark != charset
+ if (dsgcache != NULL &&
+ dsgcache->mark == charset)
+ dsg = dsgcache;
+ else {
+ for (dsg = CONFIG_DESIGNATIONS;
+ dsg->mark != charset
#ifdef Py_DEBUG
- && dsg->mark != '\0'
+ && dsg->mark != '\0'
#endif
- ;dsg++)
- /* noop */;
- assert(dsg->mark != '\0');
- dsgcache = dsg;
- }
+ ; dsg++)
+ {
+ /* noop */
+ }
+ assert(dsg->mark != '\0');
+ dsgcache = dsg;
+ }
- REQUIRE_INBUF(dsg->width)
- decoded = dsg->decoder(*inbuf);
- if (decoded == MAP_UNMAPPABLE)
- return dsg->width;
+ REQUIRE_INBUF(dsg->width);
+ decoded = dsg->decoder(*inbuf);
+ if (decoded == MAP_UNMAPPABLE)
+ return dsg->width;
- if (decoded < 0x10000) {
- OUTCHAR(decoded);
- }
- else if (decoded < 0x30000) {
- OUTCHAR(decoded);
- }
- else { /* JIS X 0213 pairs */
+ if (decoded < 0x10000) {
+ OUTCHAR(decoded);
+ }
+ else if (decoded < 0x30000) {
+ OUTCHAR(decoded);
+ }
+ else { /* JIS X 0213 pairs */
OUTCHAR2(decoded >> 16, decoded & 0xffff);
}
NEXT_IN(dsg->width);
@@ -800,9 +804,10 @@
else
return MAP_UNMAPPABLE;
return coded;
+
case 2: /* second character of unicode pair */
coded = find_pairencmap((ucs2_t)data[0], (ucs2_t)data[1],
- jisx0213_pair_encmap, JISX0213_ENCPAIRS);
+ jisx0213_pair_encmap, JISX0213_ENCPAIRS);
if (coded == DBCINV) {
*length = 1;
coded = find_pairencmap((ucs2_t)data[0], 0,
@@ -812,14 +817,17 @@
}
else
return coded;
+
case -1: /* flush unterminated */
*length = 1;
coded = find_pairencmap((ucs2_t)data[0], 0,
- jisx0213_pair_encmap, JISX0213_ENCPAIRS);
+ jisx0213_pair_encmap, JISX0213_ENCPAIRS);
if (coded == DBCINV)
return MAP_UNMAPPABLE;
else
return coded;
+ break;
+
default:
return MAP_UNMAPPABLE;
}
diff --git a/Modules/cjkcodecs/_codecs_jp.c b/Modules/cjkcodecs/_codecs_jp.c
--- a/Modules/cjkcodecs/_codecs_jp.c
+++ b/Modules/cjkcodecs/_codecs_jp.c
@@ -107,7 +107,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (TRYMAP_DEC(cp932ext, decoded, c, c2))
@@ -254,7 +254,7 @@
/* JIS X 0201 half-width katakana */
unsigned char c2;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (c2 >= 0xa1 && c2 <= 0xdf) {
OUTCHAR(0xfec0 + c2);
@@ -266,7 +266,7 @@
else if (c == 0x8f) {
unsigned char c2, c3;
- REQUIRE_INBUF(3)
+ REQUIRE_INBUF(3);
c2 = INBYTE2 ^ 0x80;
c3 = INBYTE3 ^ 0x80;
@@ -288,7 +288,7 @@
else {
unsigned char c2;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c ^= 0x80;
c2 = INBYTE2 ^ 0x80;
@@ -395,7 +395,7 @@
/* JIS X 0201 half-width katakana */
unsigned char c2;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (c2 >= 0xa1 && c2 <= 0xdf) {
OUTCHAR(0xfec0 + c2);
@@ -407,7 +407,7 @@
else if (c == 0x8f) {
unsigned char c2, c3;
- REQUIRE_INBUF(3)
+ REQUIRE_INBUF(3);
c2 = INBYTE2;
c3 = INBYTE3;
/* JIS X 0212 */
@@ -421,7 +421,7 @@
else {
unsigned char c2;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
/* JIS X 0208 */
#ifndef STRICT_BUILD
@@ -521,7 +521,7 @@
else if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xea)){
unsigned char c1, c2;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (c2 < 0x40 || (c2 > 0x7e && c2 < 0x80) || c2 > 0xfc)
return 1;
@@ -638,7 +638,8 @@
c1 = code >> 8;
c2 = (code & 0xff) - 0x21;
- if (c1 & 0x80) { /* Plane 2 */
+ if (c1 & 0x80) {
+ /* Plane 2 */
if (c1 >= 0xee)
c1 -= 0x87;
else if (c1 >= 0xac || c1 == 0xa8)
@@ -673,7 +674,7 @@
unsigned char c1, c2;
Py_UCS4 code, decoded;
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (c2 < 0x40 || (c2 > 0x7e && c2 < 0x80) || c2 > 0xfc)
return 1;
diff --git a/Modules/cjkcodecs/_codecs_kr.c b/Modules/cjkcodecs/_codecs_kr.c
--- a/Modules/cjkcodecs/_codecs_kr.c
+++ b/Modules/cjkcodecs/_codecs_kr.c
@@ -58,9 +58,10 @@
OUTBYTE2((code & 0xFF) | 0x80);
NEXT(1, 2);
}
- else { /* Mapping is found in CP949 extension,
- * but we encode it in KS X 1001:1998 Annex 3,
- * make-up sequence for EUC-KR. */
+ else {
+ /* Mapping is found in CP949 extension,
+ but we encode it in KS X 1001:1998 Annex 3,
+ make-up sequence for EUC-KR. */
REQUIRE_OUTBUF(8);
@@ -115,14 +116,14 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (c == EUCKR_JAMO_FIRSTBYTE &&
INBYTE2 == EUCKR_JAMO_FILLER) {
/* KS X 1001:1998 Annex 3 make-up sequence */
DBCHAR cho, jung, jong;
- REQUIRE_INBUF(8)
+ REQUIRE_INBUF(8);
if ((*inbuf)[2] != EUCKR_JAMO_FIRSTBYTE ||
(*inbuf)[4] != EUCKR_JAMO_FIRSTBYTE ||
(*inbuf)[6] != EUCKR_JAMO_FIRSTBYTE)
@@ -212,7 +213,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (TRYMAP_DEC(ksx1001, decoded, c ^ 0x80, INBYTE2 ^ 0x80))
OUTCHAR(decoded);
else if (TRYMAP_DEC(cp949ext, decoded, c, INBYTE2))
@@ -369,7 +370,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
c2 = INBYTE2;
if (c < 0xd8) {
diff --git a/Modules/cjkcodecs/_codecs_tw.c b/Modules/cjkcodecs/_codecs_tw.c
--- a/Modules/cjkcodecs/_codecs_tw.c
+++ b/Modules/cjkcodecs/_codecs_tw.c
@@ -54,7 +54,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (TRYMAP_DEC(big5, decoded, c, INBYTE2)) {
OUTCHAR(decoded);
NEXT_IN(2);
@@ -113,7 +113,7 @@
continue;
}
- REQUIRE_INBUF(2)
+ REQUIRE_INBUF(2);
if (TRYMAP_DEC(cp950ext, decoded, c, INBYTE2))
OUTCHAR(decoded);
diff --git a/Modules/cjkcodecs/cjkcodecs.h b/Modules/cjkcodecs/cjkcodecs.h
--- a/Modules/cjkcodecs/cjkcodecs.h
+++ b/Modules/cjkcodecs/cjkcodecs.h
@@ -113,8 +113,11 @@
} while (0)
#define REQUIRE_INBUF(n) \
- if (inleft < (n)) \
- return MBERR_TOOFEW;
+ do { \
+ if (inleft < (n)) \
+ return MBERR_TOOFEW; \
+ } while (0)
+
#define REQUIRE_OUTBUF(n) \
do { \
if (outleft < (n)) \
diff --git a/Modules/cjkcodecs/emu_jisx0213_2000.h b/Modules/cjkcodecs/emu_jisx0213_2000.h
--- a/Modules/cjkcodecs/emu_jisx0213_2000.h
+++ b/Modules/cjkcodecs/emu_jisx0213_2000.h
@@ -2,7 +2,7 @@
* standards. */
#ifndef EMULATE_JISX0213_2000_ENCODE_INVALID
-#define EMULATE_JISX0213_2000_ENCODE_INVALID 1
+# define EMULATE_JISX0213_2000_ENCODE_INVALID 1
#endif
#define EMULATE_JISX0213_2000_ENCODE_BMP(assi, c) \
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list