Merge branch 'en/xdiff-cleanup-2' into seen

Code clean-up.

Comments?

* en/xdiff-cleanup-2:
  xdiff: rename rindex -> reference_index
  xdiff: change rindex from long to size_t in xdfile_t
  xdiff: make xdfile_t.nreff a size_t instead of long
  xdiff: make xdfile_t.nrec a size_t instead of long
  xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash
  xdiff: use unambiguous types in xdl_hash_record()
  xdiff: use size_t for xrecord_t.size
  xdiff: make xrecord_t.ptr a uint8_t instead of char
  xdiff: use ssize_t for dstart/dend, make them last in xdfile_t
  doc: define unambiguous type mappings across C and Rust

11 files changed, 338 insertions, 109 deletions

diff --git a/Documentation/technical/unambiguous-types.adoc b/Documentation/technical/unambiguous-types.adoc
new file mode 100644
index 0000000000..658a5b578e
--- /dev/null
+++ b/Documentation/technical/unambiguous-types.adoc
@@ -0,0 +1,229 @@
+= Unambiguous types
+
+Most of these mappings are obvious, but there are some nuances and gotchas with
+Rust FFI (Foreign Function Interface).
+
+This document defines clear, one-to-one mappings between primitive types in C,
+Rust (and possible other languages in the future). Its purpose is to eliminate
+ambiguity in type widths, signedness, and binary representation across
+platforms and languages.
+
+For Git, the only header required to use these unambiguous types in C is
+`git-compat-util.h`.
+
+== Boolean types
+[cols="1,1", options="header"]
+|===
+| C Type | Rust Type
+| bool^1^       | bool
+|===
+
+== Integer types
+
+In C, `<stdint.h>` (or an equivalent) must be included.
+
+[cols="1,1", options="header"]
+|===
+| C Type | Rust Type
+| uint8_t    | u8
+| uint16_t   | u16
+| uint32_t   | u32
+| uint64_t   | u64
+
+| int8_t     | i8
+| int16_t    | i16
+| int32_t    | i32
+| int64_t    | i64
+|===
+
+== Floating-point types
+
+Rust requires IEEE-754 semantics.
+In C, that is typically true, but not guaranteed by the standard.
+
+[cols="1,1", options="header"]
+|===
+| C Type | Rust Type
+| float^2^      | f32
+| double^2^     | f64
+|===
+
+== Size types
+
+These types represent pointer-sized integers and are typically defined in
+`<stddef.h>` or an equivalent header.
+
+Size types should be used any time pointer arithmetic is performed e.g.
+indexing an array, describing the number of elements in memory, etc...
+
+[cols="1,1", options="header"]
+|===
+| C Type | Rust Type
+| size_t^3^     | usize
+| ptrdiff_t^4^  | isize
+|===
+
+== Character types
+
+This is where C and Rust don't have a clean one-to-one mapping. A C `char` is
+an 8-bit type that is signless (neither signed nor unsigned) which causes
+problems with e.g. `make DEVELOPER=1`. Rust's `char` type is an unsigned 32-bit
+integer that is used to describe Unicode code points. Even though a C `char`
+is the same width as `u8`, `char` should be converted to u8 where it is
+describing bytes in memory. If a C `char` is not describing bytes, then it
+should be converted to a more accurate unambiguous type.
+
+While you could specify `char` in the C code and `u8` in Rust code, it's not as
+clear what the appropriate type is, but it would work across the FFI boundary.
+However the bigger problem comes from code generation tools like cbindgen and
+bindgen. When cbindgen see u8 in Rust it will generate uint8_t on the C side
+which will cause differ in signedness warnings/errors. Similaraly if bindgen
+see `char` on the C side it will generate `std::ffi::c_char` which has its own
+problems.
+
+=== Notes
+^1^ This is only true if stdbool.h (or equivalent) is used. +
+^2^ C does not enforce IEEE-754 compatibility, but Rust expects it. If the
+platform/arch for C does not follow IEEE-754 then this equivalence does not
+hold. Also, it's assumed that `float` is 32 bits and `double` is 64, but
+there may be a strange platform/arch where even this isn't true. +
+^3^ C also defines uintptr_t, but this should not be used in Git. +
+^4^ C also defines ssize_t and intptr_t, but these should not be used in Git. +
+
+== Problems with std::ffi::c_* types in Rust
+TL;DR: They're not guaranteed to match C types for all possible C
+compilers/platforms/architectures.
+
+Only a few of Rust's C FFI types are considered safe and semantically clear to
+use: +
+
+* `c_void`
+* `CStr`
+* `CString`
+
+Even then, they should be used sparingly, and only where the semantics match
+exactly.
+
+The std::os::raw::c_* (which is deprecated) directly inherits the problems of
+core::ffi, which changes over time and seems to make a best guess at the
+correct definition for a given platform/target. This probably isn't a problem
+for all platforms that Rust supports currently, but can anyone say that Rust
+got it right for all C compilers of all platforms/targets?
+
+On top of all of that we're targeting an older version of Rust which doesn't
+have the latest mappings.
+
+To give an example: c_long is defined in
+footnote:[https://doc.rust-lang.org/1.63.0/src/core/ffi/mod.rs.html#175-189[c_long in 1.63.0]]
+footnote:[https://doc.rust-lang.org/1.89.0/src/core/ffi/primitives.rs.html#135-151[c_long in 1.89.0]]
+
+=== Rust version 1.63.0
+
+[source]
+----
+mod c_long_definition {
+    cfg_if! {
+        if #[cfg(all(target_pointer_width = "64", not(windows)))] {
+            pub type c_long = i64;
+            pub type NonZero_c_long = crate::num::NonZeroI64;
+            pub type c_ulong = u64;
+            pub type NonZero_c_ulong = crate::num::NonZeroU64;
+        } else {
+            // The minimal size of `long` in the C standard is 32 bits
+            pub type c_long = i32;
+            pub type NonZero_c_long = crate::num::NonZeroI32;
+            pub type c_ulong = u32;
+            pub type NonZero_c_ulong = crate::num::NonZeroU32;
+        }
+    }
+}
+----
+
+=== Rust version 1.89.0
+
+[source]
+----
+mod c_long_definition {
+    crate::cfg_select! {
+        any(
+            all(target_pointer_width = "64", not(windows)),
+            // wasm32 Linux ABI uses 64-bit long
+            all(target_arch = "wasm32", target_os = "linux")
+        ) => {
+            pub(super) type c_long = i64;
+            pub(super) type c_ulong = u64;
+        }
+        _ => {
+            // The minimal size of `long` in the C standard is 32 bits
+            pub(super) type c_long = i32;
+            pub(super) type c_ulong = u32;
+        }
+    }
+}
+----
+
+Even for the cases where C types are correctly mapped to Rust types via
+std::ffi::c_* there are still problems. Let's take c_char for example. On some
+platforms it's u8 on others it's i8.
+
+=== Subtraction underflow in debug mode
+
+The following code will panic in debug on platforms that define c_char as u8,
+but won't if it's an i8.
+
+[source]
+----
+let mut x: std::ffi::c_char = 0;
+x -= 1;
+----
+
+=== Inconsistent shift behavior
+
+`x` will be 0xC0 for platforms that use i8, but will be 0x40 where it's u8.
+
+[source]
+----
+let mut x: std::ffi::c_char = 0x80;
+x >>= 1;
+----
+
+=== Equality fails to compile on some platforms
+
+The following will not compile on platforms that define c_char as i8, but will
+if it's u8. You can cast x e.g. `assert_eq!(x as u8, b'a');`, but then you get
+a warning on platforms that use u8 and a clean compilation where i8 is used.
+
+[source]
+----
+let mut x: std::ffi::c_char = 0x61;
+assert_eq!(x, b'a');
+----
+
+== Enum types
+Rust enum types should not be used as FFI types. Rust enum types are more like
+C union types than C enum's. For something like:
+
+[source]
+----
+#[repr(C, u8)]
+enum Fruit {
+    Apple,
+    Banana,
+    Cherry,
+}
+----
+
+It's easy enough to make sure the Rust enum matches what C would expect, but a
+more complex type like.
+
+[source]
+----
+enum HashResult {
+    SHA1([u8; 20]),
+    SHA256([u8; 32]),
+}
+----
+
+The Rust compiler has to add a discriminant to the enum to distinguish between
+the variants. The width, location, and values for that discriminant is up to
+the Rust compiler and is not ABI stable.
diff --git a/xdiff-interface.c b/xdiff-interface.c
index 4971f722b3..1a35556380 100644
--- a/xdiff-interface.c
+++ b/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,
diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c
index 6f3998ee54..8eb664be3e 100644
--- a/xdiff/xdiffi.c
+++ b/xdiff/xdiffi.c
@@ -22,9 +22,9 @@
 
 #include "xinclude.h"
 
-static unsigned long get_hash(xdfile_t *xdf, long index)
+static size_t get_hash(xdfile_t *xdf, long index)
 {
-	return xdf->recs[xdf->rindex[index]].ha;
+	return xdf->recs[xdf->reference_index[index]].minimal_perfect_hash;
 }
 
 #define XDL_MAX_COST_MIN 256
@@ -278,10 +278,10 @@ int xdl_recs_cmp(xdfile_t *xdf1, long off1, long lim1,
 	 */
 	if (off1 == lim1) {
 		for (; off2 < lim2; off2++)
-			xdf2->changed[xdf2->rindex[off2]] = true;
+			xdf2->changed[xdf2->reference_index[off2]] = true;
 	} else if (off2 == lim2) {
 		for (; off1 < lim1; off1++)
-			xdf1->changed[xdf1->rindex[off1]] = true;
+			xdf1->changed[xdf1->reference_index[off1]] = true;
 	} else {
 		xdpsplit_t spl;
 		spl.i1 = spl.i2 = 0;
@@ -385,7 +385,7 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,
 
 static int recs_match(xrecord_t *rec1, xrecord_t *rec2)
 {
-	return (rec1->ha == rec2->ha);
+	return rec1->minimal_perfect_hash == rec2->minimal_perfect_hash;
 }
 
 /*
@@ -403,11 +403,10 @@ static int recs_match(xrecord_t *rec1, xrecord_t *rec2)
  */
 static int get_indent(xrecord_t *rec)
 {
-	long i;
 	int ret = 0;
 
-	for (i = 0; i < rec->size; i++) {
-		char c = rec->ptr[i];
+	for (size_t i = 0; i < rec->size; i++) {
+		uint8_t c = rec->ptr[i];
 
 		if (!XDL_ISSPACE(c))
 			return ret;
@@ -484,7 +483,7 @@ static void measure_split(const xdfile_t *xdf, long split,
 {
 	long i;
 
-	if (split >= xdf->nrec) {
+	if (split >= (long)xdf->nrec) {
 		m->end_of_file = 1;
 		m->indent = -1;
 	} else {
@@ -507,7 +506,7 @@ static void measure_split(const xdfile_t *xdf, long split,
 
 	m->post_blank = 0;
 	m->post_indent = -1;
-	for (i = split + 1; i < xdf->nrec; i++) {
+	for (i = split + 1; i < (long)xdf->nrec; i++) {
 		m->post_indent = get_indent(&xdf->recs[i]);
 		if (m->post_indent != -1)
 			break;
@@ -718,7 +717,7 @@ static void group_init(xdfile_t *xdf, struct xdlgroup *g)
  */
 static inline int group_next(xdfile_t *xdf, struct xdlgroup *g)
 {
-	if (g->end == xdf->nrec)
+	if (g->end == (long)xdf->nrec)
 		return -1;
 
 	g->start = g->end + 1;
@@ -751,7 +750,7 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
  */
 static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g)
 {
-	if (g->end < xdf->nrec &&
+	if (g->end < (long)xdf->nrec &&
 	    recs_match(&xdf->recs[g->start], &xdf->recs[g->end])) {
 		xdf->changed[g->start++] = false;
 		xdf->changed[g->end++] = true;
@@ -993,11 +992,11 @@ static void xdl_mark_ignorable_lines(xdchange_t *xscr, xdfenv_t *xe, long flags)
 
 		rec = &xe->xdf1.recs[xch->i1];
 		for (i = 0; i < xch->chg1 && ignore; i++)
-			ignore = xdl_blankline(rec[i].ptr, rec[i].size, flags);
+			ignore = xdl_blankline((const char *)rec[i].ptr, (long)rec[i].size, flags);
 
 		rec = &xe->xdf2.recs[xch->i2];
 		for (i = 0; i < xch->chg2 && ignore; i++)
-			ignore = xdl_blankline(rec[i].ptr, rec[i].size, flags);
+			ignore = xdl_blankline((const char *)rec[i].ptr, (long)rec[i].size, flags);
 
 		xch->ignore = ignore;
 	}
@@ -1008,7 +1007,7 @@ static int record_matches_regex(xrecord_t *rec, xpparam_t const *xpp) {
 	size_t i;
 
 	for (i = 0; i < xpp->ignore_regex_nr; i++)
-		if (!regexec_buf(xpp->ignore_regex[i], rec->ptr, rec->size, 1,
+		if (!regexec_buf(xpp->ignore_regex[i], (const char *)rec->ptr, rec->size, 1,
 				 &regmatch, 0))
 			return 1;
 
diff --git a/xdiff/xemit.c b/xdiff/xemit.c
index b2f1f30cd3..04f7e9193b 100644
--- a/xdiff/xemit.c
+++ b/xdiff/xemit.c
@@ -27,7 +27,7 @@ static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *
 {
 	xrecord_t *rec = &xdf->recs[ri];
 
-	if (xdl_emit_diffrec(rec->ptr, rec->size, pre, strlen(pre), ecb) < 0)
+	if (xdl_emit_diffrec((char const *)rec->ptr, (long)rec->size, pre, strlen(pre), ecb) < 0)
 		return -1;
 
 	return 0;
@@ -113,8 +113,8 @@ static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri,
 	xrecord_t *rec = &xdf->recs[ri];
 
 	if (!xecfg->find_func)
-		return def_ff(rec->ptr, rec->size, buf, sz);
-	return xecfg->find_func(rec->ptr, rec->size, buf, sz, xecfg->find_func_priv);
+		return def_ff((const char *)rec->ptr, (long)rec->size, buf, sz);
+	return xecfg->find_func((const char *)rec->ptr, (long)rec->size, buf, sz, xecfg->find_func_priv);
 }
 
 static int is_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri)
@@ -137,7 +137,7 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg,
 	buf = func_line ? func_line->buf : dummy;
 	size = func_line ? sizeof(func_line->buf) : sizeof(dummy);
 
-	for (l = start; l != limit && 0 <= l && l < xe->xdf1.nrec; l += step) {
+	for (l = start; l != limit && 0 <= l && l < (long)xe->xdf1.nrec; l += step) {
 		long len = match_func_rec(&xe->xdf1, xecfg, l, buf, size);
 		if (len >= 0) {
 			if (func_line)
@@ -151,7 +151,7 @@ static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg,
 static int is_empty_rec(xdfile_t *xdf, long ri)
 {
 	xrecord_t *rec = &xdf->recs[ri];
-	long i = 0;
+	size_t i = 0;
 
 	for (; i < rec->size && XDL_ISSPACE(rec->ptr[i]); i++);
 
@@ -179,14 +179,14 @@ pre_context_calculation:
 			long fs1, i1 = xch->i1;
 
 			/* Appended chunk? */
-			if (i1 >= xe->xdf1.nrec) {
+			if (i1 >= (long)xe->xdf1.nrec) {
 				long i2 = xch->i2;
 
 				/*
 				 * We don't need additional context if
 				 * a whole function was added.
 				 */
-				while (i2 < xe->xdf2.nrec) {
+				while (i2 < (long)xe->xdf2.nrec) {
 					if (is_func_rec(&xe->xdf2, xecfg, i2))
 						goto post_context_calculation;
 					i2++;
@@ -196,7 +196,7 @@ pre_context_calculation:
 				 * Otherwise get more context from the
 				 * pre-image.
 				 */
-				i1 = xe->xdf1.nrec - 1;
+				i1 = (long)xe->xdf1.nrec - 1;
 			}
 
 			fs1 = get_func_line(xe, xecfg, NULL, i1, -1);
@@ -228,8 +228,8 @@ pre_context_calculation:
 
  post_context_calculation:
 		lctx = xecfg->ctxlen;
-		lctx = XDL_MIN(lctx, xe->xdf1.nrec - (xche->i1 + xche->chg1));
-		lctx = XDL_MIN(lctx, xe->xdf2.nrec - (xche->i2 + xche->chg2));
+		lctx = XDL_MIN(lctx, (long)xe->xdf1.nrec - (xche->i1 + xche->chg1));
+		lctx = XDL_MIN(lctx, (long)xe->xdf2.nrec - (xche->i2 + xche->chg2));
 
 		e1 = xche->i1 + xche->chg1 + lctx;
 		e2 = xche->i2 + xche->chg2 + lctx;
@@ -237,13 +237,13 @@ pre_context_calculation:
 		if (xecfg->flags & XDL_EMIT_FUNCCONTEXT) {
 			long fe1 = get_func_line(xe, xecfg, NULL,
 						 xche->i1 + xche->chg1,
-						 xe->xdf1.nrec);
+						 (long)xe->xdf1.nrec);
 			while (fe1 > 0 && is_empty_rec(&xe->xdf1, fe1 - 1))
 				fe1--;
 			if (fe1 < 0)
-				fe1 = xe->xdf1.nrec;
+				fe1 = (long)xe->xdf1.nrec;
 			if (fe1 > e1) {
-				e2 = XDL_MIN(e2 + (fe1 - e1), xe->xdf2.nrec);
+				e2 = XDL_MIN(e2 + (fe1 - e1), (long)xe->xdf2.nrec);
 				e1 = fe1;
 			}
 
@@ -254,7 +254,7 @@ pre_context_calculation:
 			 */
 			if (xche->next) {
 				long l = XDL_MIN(xche->next->i1,
-						 xe->xdf1.nrec - 1);
+						 (long)xe->xdf1.nrec - 1);
 				if (l - xecfg->ctxlen <= e1 ||
 				    get_func_line(xe, xecfg, NULL, l, e1) < 0) {
 					xche = xche->next;
diff --git a/xdiff/xhistogram.c b/xdiff/xhistogram.c
index 6dc450b1fe..5ae1282c27 100644
--- a/xdiff/xhistogram.c
+++ b/xdiff/xhistogram.c
@@ -90,7 +90,7 @@ struct region {
 
 static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
 {
-	return r1->ha == r2->ha;
+	return r1->minimal_perfect_hash == r2->minimal_perfect_hash;
 
 }
 
@@ -98,7 +98,7 @@ static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
 	(cmp_recs(REC(i->env, s1, l1), REC(i->env, s2, l2)))
 
 #define TABLE_HASH(index, side, line) \
-	XDL_HASHLONG((REC(index->env, side, line))->ha, index->table_bits)
+	XDL_HASHLONG((REC(index->env, side, line))->minimal_perfect_hash, index->table_bits)
 
 static int scanA(struct histindex *index, int line1, int count1)
 {
diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c
index fd600cbb5d..29dad98c49 100644
--- a/xdiff/xmerge.c
+++ b/xdiff/xmerge.c
@@ -101,8 +101,8 @@ static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2,
 	xrecord_t *rec2 = xe2->xdf2.recs + i2;
 
 	for (i = 0; i < line_count; i++) {
-		int result = xdl_recmatch(rec1[i].ptr, rec1[i].size,
-			rec2[i].ptr, rec2[i].size, flags);
+		int result = xdl_recmatch((const char *)rec1[i].ptr, (long)rec1[i].size,
+			(const char *)rec2[i].ptr, (long)rec2[i].size, flags);
 		if (!result)
 			return -1;
 	}
@@ -119,11 +119,11 @@ static int xdl_recs_copy_0(int use_orig, xdfenv_t *xe, int i, int count, int nee
 	if (count < 1)
 		return 0;
 
-	for (i = 0; i < count; size += recs[i++].size)
+	for (i = 0; i < count; size += (int)recs[i++].size)
 		if (dest)
 			memcpy(dest + size, recs[i].ptr, recs[i].size);
 	if (add_nl) {
-		i = recs[count - 1].size;
+		i = (int)recs[count - 1].size;
 		if (i == 0 || recs[count - 1].ptr[i - 1] != '\n') {
 			if (needs_cr) {
 				if (dest)
@@ -156,9 +156,9 @@ static int xdl_orig_copy(xdfenv_t *xe, int i, int count, int needs_cr, int add_n
  */
 static int is_eol_crlf(xdfile_t *file, int i)
 {
-	long size;
+	size_t size;
 
-	if (i < file->nrec - 1)
+	if (i < (long)file->nrec - 1)
 		/* All lines before the last *must* end in LF */
 		return (size = file->recs[i].size) > 1 &&
 			file->recs[i].ptr[size - 2] == '\r';
@@ -317,15 +317,15 @@ static int xdl_fill_merge_buffer(xdfenv_t *xe1, const char *name1,
 			continue;
 		i = m->i1 + m->chg1;
 	}
-	size += xdl_recs_copy(xe1, i, xe1->xdf2.nrec - i, 0, 0,
+	size += xdl_recs_copy(xe1, i, (int)xe1->xdf2.nrec - i, 0, 0,
 			      dest ? dest + size : NULL);
 	return size;
 }
 
 static int recmatch(xrecord_t *rec1, xrecord_t *rec2, unsigned long flags)
 {
-	return xdl_recmatch(rec1->ptr, rec1->size,
-			    rec2->ptr, rec2->size, flags);
+	return xdl_recmatch((const char *)rec1->ptr, (long)rec1->size,
+			    (const char *)rec2->ptr, (long)rec2->size, flags);
 }
 
 /*
@@ -382,10 +382,10 @@ static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m,
 		 * we have a very simple mmfile structure.
 		 */
 		t1.ptr = (char *)xe1->xdf2.recs[m->i1].ptr;
-		t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1].ptr
+		t1.size = (char *)xe1->xdf2.recs[m->i1 + m->chg1 - 1].ptr
 			+ xe1->xdf2.recs[m->i1 + m->chg1 - 1].size - t1.ptr;
 		t2.ptr = (char *)xe2->xdf2.recs[m->i2].ptr;
-		t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1].ptr
+		t2.size = (char *)xe2->xdf2.recs[m->i2 + m->chg2 - 1].ptr
 			+ xe2->xdf2.recs[m->i2 + m->chg2 - 1].size - t2.ptr;
 		if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0)
 			return -1;
@@ -440,8 +440,8 @@ static int line_contains_alnum(const char *ptr, long size)
 static int lines_contain_alnum(xdfenv_t *xe, int i, int chg)
 {
 	for (; chg; chg--, i++)
-		if (line_contains_alnum(xe->xdf2.recs[i].ptr,
-				xe->xdf2.recs[i].size))
+		if (line_contains_alnum((const char *)xe->xdf2.recs[i].ptr,
+				(long)xe->xdf2.recs[i].size))
 			return 1;
 	return 0;
 }
@@ -622,7 +622,7 @@ static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1,
 			changes = c;
 		i0 = xscr1->i1;
 		i1 = xscr1->i2;
-		i2 = xscr1->i1 + xe2->xdf2.nrec - xe2->xdf1.nrec;
+		i2 = xscr1->i1 + (long)xe2->xdf2.nrec - (long)xe2->xdf1.nrec;
 		chg0 = xscr1->chg1;
 		chg1 = xscr1->chg2;
 		chg2 = xscr1->chg1;
@@ -637,7 +637,7 @@ static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1,
 		if (!changes)
 			changes = c;
 		i0 = xscr2->i1;
-		i1 = xscr2->i1 + xe1->xdf2.nrec - xe1->xdf1.nrec;
+		i1 = xscr2->i1 + (long)xe1->xdf2.nrec - (long)xe1->xdf1.nrec;
 		i2 = xscr2->i2;
 		chg0 = xscr2->chg1;
 		chg1 = xscr2->chg1;
diff --git a/xdiff/xpatience.c b/xdiff/xpatience.c
index 669b653580..a0b31eb5d8 100644
--- a/xdiff/xpatience.c
+++ b/xdiff/xpatience.c
@@ -48,7 +48,7 @@
 struct hashmap {
 	int nr, alloc;
 	struct entry {
-		unsigned long hash;
+		size_t minimal_perfect_hash;
 		/*
 		 * 0 = unused entry, 1 = first line, 2 = second, etc.
 		 * line2 is NON_UNIQUE if the line is not unique
@@ -101,10 +101,10 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
 	 * So we multiply ha by 2 in the hope that the hashing was
 	 * "unique enough".
 	 */
-	int index = (int)((record->ha << 1) % map->alloc);
+	int index = (int)((record->minimal_perfect_hash << 1) % map->alloc);
 
 	while (map->entries[index].line1) {
-		if (map->entries[index].hash != record->ha) {
+		if (map->entries[index].minimal_perfect_hash != record->minimal_perfect_hash) {
 			if (++index >= map->alloc)
 				index = 0;
 			continue;
@@ -120,8 +120,8 @@ static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
 	if (pass == 2)
 		return;
 	map->entries[index].line1 = line;
-	map->entries[index].hash = record->ha;
-	map->entries[index].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1].ptr);
+	map->entries[index].minimal_perfect_hash = record->minimal_perfect_hash;
+	map->entries[index].anchor = is_anchor(xpp, (const char *)map->env->xdf1.recs[line - 1].ptr);
 	if (!map->first)
 		map->first = map->entries + index;
 	if (map->last) {
@@ -248,7 +248,7 @@ static int match(struct hashmap *map, int line1, int line2)
 {
 	xrecord_t *record1 = &map->env->xdf1.recs[line1 - 1];
 	xrecord_t *record2 = &map->env->xdf2.recs[line2 - 1];
-	return record1->ha == record2->ha;
+	return record1->minimal_perfect_hash == record2->minimal_perfect_hash;
 }
 
 static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
@@ -370,5 +370,5 @@ static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
 
 int xdl_do_patience_diff(xpparam_t const *xpp, xdfenv_t *env)
 {
-	return patience_diff(xpp, env, 1, env->xdf1.nrec, 1, env->xdf2.nrec);
+	return patience_diff(xpp, env, 1, (int)env->xdf1.nrec, 1, (int)env->xdf2.nrec);
 }
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index 192334f1b7..1dd420a2ff 100644
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -96,11 +96,11 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t
 	long hi;
 	xdlclass_t *rcrec;
 
-	hi = (long) XDL_HASHLONG(rec->ha, cf->hbits);
+	hi = (long) XDL_HASHLONG(rec->line_hash, cf->hbits);
 	for (rcrec = cf->rchash[hi]; rcrec; rcrec = rcrec->next)
-		if (rcrec->rec.ha == rec->ha &&
-				xdl_recmatch(rcrec->rec.ptr, rcrec->rec.size,
-					rec->ptr, rec->size, cf->flags))
+		if (rcrec->rec.line_hash == rec->line_hash &&
+				xdl_recmatch((const char *)rcrec->rec.ptr, (long)rcrec->rec.size,
+					(const char *)rec->ptr, (long)rec->size, cf->flags))
 			break;
 
 	if (!rcrec) {
@@ -120,7 +120,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t
 
 	(pass == 1) ? rcrec->len1++ : rcrec->len2++;
 
-	rec->ha = (unsigned long) rcrec->idx;
+	rec->minimal_perfect_hash = (size_t)rcrec->idx;
 
 	return 0;
 }
@@ -128,7 +128,7 @@ static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t
 
 static void xdl_free_ctx(xdfile_t *xdf)
 {
-	xdl_free(xdf->rindex);
+	xdl_free(xdf->reference_index);
 	xdl_free(xdf->changed - 1);
 	xdl_free(xdf->recs);
 }
@@ -137,11 +137,11 @@ 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;
+	xdf->reference_index = NULL;
 	xdf->changed = NULL;
 	xdf->recs = NULL;
 
@@ -153,12 +153,12 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 		for (top = blk + bsize; cur < top; ) {
 			prev = cur;
 			hav = xdl_hash_record(&cur, top, xpp->flags);
-			if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec))
+			if (XDL_ALLOC_GROW(xdf->recs, (long)xdf->nrec + 1, narec))
 				goto abort;
 			crec = &xdf->recs[xdf->nrec++];
 			crec->ptr = prev;
-			crec->size = (long) (cur - prev);
-			crec->ha = hav;
+			crec->size = cur - prev;
+			crec->line_hash = hav;
 			if (xdl_classify_record(pass, cf, crec) < 0)
 				goto abort;
 		}
@@ -169,7 +169,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 
 	if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) &&
 	    (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) {
-		if (!XDL_ALLOC_ARRAY(xdf->rindex, xdf->nrec + 1))
+		if (!XDL_ALLOC_ARRAY(xdf->reference_index, xdf->nrec + 1))
 			goto abort;
 	}
 
@@ -264,7 +264,7 @@ static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) {
  * might be potentially discarded if they appear in a run of discardable.
  */
 static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
-	long i, nm, nreff, mlim;
+	long i, nm, mlim;
 	xrecord_t *recs;
 	xdlclass_t *rcrec;
 	uint8_t *action1 = NULL, *action2 = NULL;
@@ -287,18 +287,18 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
 	/*
 	 * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE.
 	 */
-	if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT)
+	if ((mlim = xdl_bogosqrt((long)xdf1->nrec)) > XDL_MAX_EQLIMIT)
 		mlim = XDL_MAX_EQLIMIT;
 	for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) {
-		rcrec = cf->rcrecs[recs->ha];
+		rcrec = cf->rcrecs[recs->minimal_perfect_hash];
 		nm = rcrec ? rcrec->len2 : 0;
 		action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
 	}
 
-	if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT)
+	if ((mlim = xdl_bogosqrt((long)xdf2->nrec)) > XDL_MAX_EQLIMIT)
 		mlim = XDL_MAX_EQLIMIT;
 	for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) {
-		rcrec = cf->rcrecs[recs->ha];
+		rcrec = cf->rcrecs[recs->minimal_perfect_hash];
 		nm = rcrec ? rcrec->len1 : 0;
 		action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
 	}
@@ -307,29 +307,29 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
 	 * Use temporary arrays to decide if changed[i] should remain
 	 * false, or become true.
 	 */
-	for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];
+	xdf1->nreff = 0;
+	for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];
 	     i <= xdf1->dend; i++, recs++) {
 		if (action1[i] == KEEP ||
 		    (action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))) {
-			xdf1->rindex[nreff++] = i;
+			xdf1->reference_index[xdf1->nreff++] = i;
 			/* changed[i] remains false, i.e. keep */
 		} else
 			xdf1->changed[i] = true;
 			/* i.e. discard */
 	}
-	xdf1->nreff = nreff;
 
-	for (nreff = 0, i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart];
+	xdf2->nreff = 0;
+	for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart];
 	     i <= xdf2->dend; i++, recs++) {
 		if (action2[i] == KEEP ||
 		    (action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))) {
-			xdf2->rindex[nreff++] = i;
+			xdf2->reference_index[xdf2->nreff++] = i;
 			/* changed[i] remains false, i.e. keep */
 		} else
 			xdf2->changed[i] = true;
 			/* i.e. discard */
 	}
-	xdf2->nreff = nreff;
 
 cleanup:
 	xdl_free(action1);
@@ -348,9 +348,9 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) {
 
 	recs1 = xdf1->recs;
 	recs2 = xdf2->recs;
-	for (i = 0, lim = XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim;
+	for (i = 0, lim = (long)XDL_MIN(xdf1->nrec, xdf2->nrec); i < lim;
 	     i++, recs1++, recs2++)
-		if (recs1->ha != recs2->ha)
+		if (recs1->minimal_perfect_hash != recs2->minimal_perfect_hash)
 			break;
 
 	xdf1->dstart = xdf2->dstart = i;
@@ -358,11 +358,11 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) {
 	recs1 = xdf1->recs + xdf1->nrec - 1;
 	recs2 = xdf2->recs + xdf2->nrec - 1;
 	for (lim -= i, i = 0; i < lim; i++, recs1--, recs2--)
-		if (recs1->ha != recs2->ha)
+		if (recs1->minimal_perfect_hash != recs2->minimal_perfect_hash)
 			break;
 
-	xdf1->dend = xdf1->nrec - i - 1;
-	xdf2->dend = xdf2->nrec - i - 1;
+	xdf1->dend = (long)xdf1->nrec - i - 1;
+	xdf2->dend = (long)xdf2->nrec - i - 1;
 
 	return 0;
 }
diff --git a/xdiff/xtypes.h b/xdiff/xtypes.h
index f145abba3e..5accbec284 100644
--- a/xdiff/xtypes.h
+++ b/xdiff/xtypes.h
@@ -39,18 +39,19 @@ typedef struct s_chastore {
 } chastore_t;
 
 typedef struct s_xrecord {
-	char const *ptr;
-	long size;
-	unsigned long ha;
+	uint8_t const *ptr;
+	size_t size;
+	uint64_t line_hash;
+	size_t minimal_perfect_hash;
 } xrecord_t;
 
 typedef struct s_xdfile {
 	xrecord_t *recs;
-	long nrec;
-	long dstart, dend;
+	size_t nrec;
 	bool *changed;
-	long *rindex;
-	long nreff;
+	size_t *reference_index;
+	size_t nreff;
+	ptrdiff_t dstart, dend;
 } xdfile_t;
 
 typedef struct s_xdfenv {
diff --git a/xdiff/xutils.c b/xdiff/xutils.c
index 447e66c719..77ee1ad9c8 100644
--- a/xdiff/xutils.c
+++ b/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;
 
@@ -304,9 +304,9 @@ 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
@@ -314,7 +314,7 @@ unsigned long xdl_hash_record_verbatim(char const **data, char const *top) {
 	 */
 	for (; ptr < top && *ptr != '\n'; ptr++) {
 		ha += (ha << 5);
-		ha += (unsigned long) *ptr;
+		ha += (uint64_t) *ptr;
 	}
 	*data = ptr < top ? ptr + 1: ptr;
 #else
@@ -465,10 +465,10 @@ int xdl_fall_back_diff(xdfenv_t *diff_env, xpparam_t const *xpp,
 	xdfenv_t env;
 
 	subfile1.ptr = (char *)diff_env->xdf1.recs[line1 - 1].ptr;
-	subfile1.size = diff_env->xdf1.recs[line1 + count1 - 2].ptr +
+	subfile1.size = (char *)diff_env->xdf1.recs[line1 + count1 - 2].ptr +
 		diff_env->xdf1.recs[line1 + count1 - 2].size - subfile1.ptr;
 	subfile2.ptr = (char *)diff_env->xdf2.recs[line2 - 1].ptr;
-	subfile2.size = diff_env->xdf2.recs[line2 + count2 - 2].ptr +
+	subfile2.size = (char *)diff_env->xdf2.recs[line2 + count2 - 2].ptr +
 		diff_env->xdf2.recs[line2 + count2 - 2].size - subfile2.ptr;
 	if (xdl_do_diff(&subfile1, &subfile2, xpp, &env) < 0)
 		return -1;
diff --git a/xdiff/xutils.h b/xdiff/xutils.h
index 13f6831047..615b4a9d35 100644
--- a/xdiff/xutils.h
+++ b/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);