Unlocalized isspace and friends

Do our own ctype.h, just to get the sane semantics: we want
locale-independence, _and_ we want the right signed behaviour. Plus we
only use a very small subset of ctype.h anyway (isspace, isalpha,
isdigit and isalnum).

Signed-off-by: Junio C Hamano <junkio@cox.net>

16 files changed, 51 insertions, 14 deletions

diff --git a/Makefile b/Makefile
index e2e87f6beb..9fe65ba2be 100644
--- a/Makefile
+++ b/Makefile
@@ -159,7 +159,8 @@ LIB_OBJS = \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o \
 	quote.o read-cache.o refs.o run-command.o \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
-	tag.o tree.o usage.o config.o environment.o $(DIFF_OBJS)
+	tag.o tree.o usage.o config.o environment.o ctype.o \
+	$(DIFF_OBJS)
 
 LIBS = $(LIB_FILE)
 LIBS += -lz
diff --git a/apply.c b/apply.c
index 155fbe84da..f4d00f2835 100644
--- a/apply.c
+++ b/apply.c
@@ -6,7 +6,6 @@
  * This applies patches on top of some (arbitrary) version of the SCM.
  *
  */
-#include <ctype.h>
 #include <fnmatch.h>
 #include "cache.h"
 
diff --git a/cache.h b/cache.h
index 328658235b..f1d15ab3c9 100644
--- a/cache.h
+++ b/cache.h
@@ -387,4 +387,30 @@ extern int git_config_bool(const char *, const char *);
 extern char git_default_email[MAX_GITNAME];
 extern char git_default_name[MAX_GITNAME];
 
+/* Sane ctype - no locale, and works with signed chars */
+#undef isspace
+#undef isdigit
+#undef isalpha
+#undef isalnum
+#undef tolower
+#undef toupper
+extern unsigned char sane_ctype[256];
+#define GIT_SPACE 0x01
+#define GIT_DIGIT 0x02
+#define GIT_ALPHA 0x04
+#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
+#define isspace(x) sane_istest(x,GIT_SPACE)
+#define isdigit(x) sane_istest(x,GIT_DIGIT)
+#define isalpha(x) sane_istest(x,GIT_ALPHA)
+#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
+#define tolower(x) sane_case((unsigned char)(x), 0x20)
+#define toupper(x) sane_case((unsigned char)(x), 0)
+
+static inline int sane_case(int x, int high)
+{
+	if (sane_istest(x, GIT_ALPHA))
+		x = (x & ~0x20) | high;
+	return x;
+}
+
 #endif /* CACHE_H */
diff --git a/commit-tree.c b/commit-tree.c
index 030fb704e5..ea0fdd44e2 100644
--- a/commit-tree.c
+++ b/commit-tree.c
@@ -7,7 +7,6 @@
 
 #include <pwd.h>
 #include <time.h>
-#include <ctype.h>
 
 #define BLOCKING (1ul << 14)
 
diff --git a/commit.c b/commit.c
index f735f981bb..8f403180e5 100644
--- a/commit.c
+++ b/commit.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 #include "tag.h"
 #include "commit.h"
 #include "cache.h"
diff --git a/config.c b/config.c
index 9b7c6f2942..519fecfee4 100644
--- a/config.c
+++ b/config.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 
 #include "cache.h"
 
diff --git a/convert-objects.c b/convert-objects.c
index 9ad0c77678..a892013f0f 100644
--- a/convert-objects.c
+++ b/convert-objects.c
@@ -1,6 +1,5 @@
 #define _XOPEN_SOURCE /* glibc2 needs this */
 #include <time.h>
-#include <ctype.h>
 #include "cache.h"
 
 struct entry {
diff --git a/ctype.c b/ctype.c
new file mode 100644
index 0000000000..56bdffa636
--- /dev/null
+++ b/ctype.c
@@ -0,0 +1,23 @@
+/*
+ * Sane locale-independent, ASCII ctype.
+ *
+ * No surprises, and works with signed and unsigned chars.
+ */
+#include "cache.h"
+
+#define SS GIT_SPACE
+#define AA GIT_ALPHA
+#define DD GIT_DIGIT
+
+unsigned char sane_ctype[256] = {
+	 0,  0,  0,  0,  0,  0,  0,  0,  0, SS, SS,  0,  0, SS,  0,  0,		/* 0-15 */
+	 0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,		/* 16-15 */
+	SS,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,		/* 32-15 */
+	DD, DD, DD, DD, DD, DD, DD, DD, DD, DD,  0,  0,  0,  0,  0,  0,		/* 48-15 */
+	 0, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA,		/* 64-15 */
+	AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA,  0,  0,  0,  0,  0,		/* 80-15 */
+	 0, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA,		/* 96-15 */
+	AA, AA, AA, AA, AA, AA, AA, AA, AA, AA, AA,  0,  0,  0,  0,  0,		/* 112-15 */
+	/* Nothing in the 128.. range */
+};
+
diff --git a/date.c b/date.c
index b21cadc4d6..63f5a09197 100644
--- a/date.c
+++ b/date.c
@@ -4,7 +4,6 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 
-#include <ctype.h>
 #include <time.h>
 
 #include "cache.h"
diff --git a/diff-tree.c b/diff-tree.c
index 2203fa56d0..851722037d 100644
--- a/diff-tree.c
+++ b/diff-tree.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 #include "cache.h"
 #include "diff.h"
 #include "commit.h"
diff --git a/ident.c b/ident.c
index 7a9f5672eb..1bfbc6ff35 100644
--- a/ident.c
+++ b/ident.c
@@ -9,7 +9,6 @@
 
 #include <pwd.h>
 #include <time.h>
-#include <ctype.h>
 
 static char git_default_date[50];
 
diff --git a/mailsplit.c b/mailsplit.c
index 0f8100dcca..189f4ed724 100644
--- a/mailsplit.c
+++ b/mailsplit.c
@@ -11,7 +11,6 @@
 #include <sys/stat.h>
 #include <string.h>
 #include <stdio.h>
-#include <ctype.h>
 #include <assert.h>
 #include "cache.h"
 
diff --git a/pack-objects.c b/pack-objects.c
index 8a1ee746e0..b3e6152033 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 #include "cache.h"
 #include "object.h"
 #include "delta.h"
diff --git a/patch-id.c b/patch-id.c
index 960e7cedf9..edbc4aa3e8 100644
--- a/patch-id.c
+++ b/patch-id.c
@@ -1,4 +1,3 @@
-#include <ctype.h>
 #include "cache.h"
 
 static void flush_current_id(int patchlen, unsigned char *id, SHA_CTX *c)
diff --git a/refs.c b/refs.c
index 5a8cbd4ef3..42240d2769 100644
--- a/refs.c
+++ b/refs.c
@@ -2,7 +2,6 @@
 #include "cache.h"
 
 #include <errno.h>
-#include <ctype.h>
 
 /* We allow "recursive" symbolic refs. Only within reason, though */
 #define MAXDEPTH 5
diff --git a/update-ref.c b/update-ref.c
index 4a1704c1a5..65dc3d6385 100644
--- a/update-ref.c
+++ b/update-ref.c
@@ -1,6 +1,5 @@
 #include "cache.h"
 #include "refs.h"
-#include <ctype.h>
 
 static const char git_update_ref_usage[] = "git-update-ref <refname> <value> [<oldval>]";