xdiff: use unambiguous types in xdl_hash_record()

Convert the function signature and body to use unambiguous types. char
is changed to uint8_t because this function processes bytes in memory.
unsigned long to uint64_t so that the hash output is consistent across
platforms. `flags` was changed from long to uint64_t to ensure the
high order bits are not dropped on platforms that treat long as 32
bits.

Signed-off-by: Ezekiel Newren <ezekielnewren@gmail.com>

Author: ezekielnewren

xdiff-interface.c

@@ -300,7 +300,7 @@ void xdiff_clear_find_func(xdemitconf_t *xecfg)
 
 unsigned long xdiff_hash_string(const char *s, size_t len, long flags)
 {
-	return xdl_hash_record(&s, s + len, flags);
+	return xdl_hash_record((uint8_t const**)&s, (uint8_t const*)s + len, flags);
 }
 
 int xdiff_compare_lines(const char *l1, long s1,

xdiff/xprepare.c

@@ -137,8 +137,8 @@ static void xdl_free_ctx(xdfile_t *xdf)
 static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
 			   xdlclassifier_t *cf, xdfile_t *xdf) {
 	long bsize;
-	unsigned long hav;
-	char const *blk, *cur, *top, *prev;
+	uint64_t hav;
+	uint8_t const *blk, *cur, *top, *prev;
 	xrecord_t *crec;
 
 	xdf->rindex = NULL;
@@ -156,7 +156,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 			if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec))
 				goto abort;
 			crec = &xdf->recs[xdf->nrec++];
-			crec->ptr = (uint8_t const *)prev;
+			crec->ptr = prev;
 			crec->size = cur - prev;
 			crec->ha = hav;
 			if (xdl_classify_record(pass, cf, crec) < 0)

xdiff/xutils.c

@@ -249,11 +249,11 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
 	return 1;
 }
 
-unsigned long xdl_hash_record_with_whitespace(char const **data,
-		char const *top, long flags) {
-	unsigned long ha = 5381;
-	char const *ptr = *data;
-	int cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL;
+uint64_t xdl_hash_record_with_whitespace(uint8_t const **data,
+		uint8_t const *top, uint64_t flags) {
+	uint64_t ha = 5381;
+	uint8_t const *ptr = *data;
+	bool cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL;
 
 	for (; ptr < top && *ptr != '\n'; ptr++) {
 		if (cr_at_eol_only) {
@@ -263,8 +263,8 @@ unsigned long xdl_hash_record_with_whitespace(char const **data,
 				continue;
 		}
 		else if (XDL_ISSPACE(*ptr)) {
-			const char *ptr2 = ptr;
-			int at_eol;
+			const uint8_t *ptr2 = ptr;
+			bool at_eol;
 			while (ptr + 1 < top && XDL_ISSPACE(ptr[1])
 					&& ptr[1] != '\n')
 				ptr++;
@@ -274,20 +274,20 @@ unsigned long xdl_hash_record_with_whitespace(char const **data,
 			else if (flags & XDF_IGNORE_WHITESPACE_CHANGE
 				 && !at_eol) {
 				ha += (ha << 5);
-				ha ^= (unsigned long) ' ';
+				ha ^= (uint64_t) ' ';
 			}
 			else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL
 				 && !at_eol) {
 				while (ptr2 != ptr + 1) {
 					ha += (ha << 5);
-					ha ^= (unsigned long) *ptr2;
+					ha ^= (uint64_t) *ptr2;
 					ptr2++;
 				}
 			}
 			continue;
 		}
 		ha += (ha << 5);
-		ha ^= (unsigned long) *ptr;
+		ha ^= (uint64_t) *ptr;
 	}
 	*data = ptr < top ? ptr + 1: ptr;
 
@@ -304,17 +304,17 @@ unsigned long xdl_hash_record_with_whitespace(char const **data,
 #define REASSOC_FENCE(x, y)
 #endif
 
-unsigned long xdl_hash_record_verbatim(char const **data, char const *top) {
-	unsigned long ha = 5381, c0, c1;
-	char const *ptr = *data;
+uint64_t xdl_hash_record_verbatim(uint8_t const **data, uint8_t const *top) {
+	uint64_t ha = 5381, c0, c1;
+	uint8_t const *ptr = *data;
 #if 0
 	/*
 	 * The baseline form of the optimized loop below. This is the djb2
 	 * hash (the above function uses a variant with XOR instead of ADD).
 	 */
 	for (; ptr < top && *ptr != '\n'; ptr++) {
 		ha += (ha << 5);
-		ha += (unsigned long) *ptr;
+		ha += (uint64_t) *ptr;
 	}
 	*data = ptr < top ? ptr + 1: ptr;
 #else

xdiff/xutils.h

@@ -34,9 +34,9 @@ void *xdl_cha_alloc(chastore_t *cha);
 long xdl_guess_lines(mmfile_t *mf, long sample);
 int xdl_blankline(const char *line, long size, long flags);
 int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
-unsigned long xdl_hash_record_verbatim(char const **data, char const *top);
-unsigned long xdl_hash_record_with_whitespace(char const **data, char const *top, long flags);
-static inline unsigned long xdl_hash_record(char const **data, char const *top, long flags)
+uint64_t xdl_hash_record_verbatim(uint8_t const **data, uint8_t const *top);
+uint64_t xdl_hash_record_with_whitespace(uint8_t const **data, uint8_t const *top, uint64_t flags);
+static inline uint64_t xdl_hash_record(uint8_t const **data, uint8_t const *top, uint64_t flags)
 {
 	if (flags & XDF_WHITESPACE_FLAGS)
 		return xdl_hash_record_with_whitespace(data, top, flags);