Cleanup reference implementation

10 files changed, 225 insertions, 191 deletions

diff --git a/Makefile b/Makefile
index 5d13272..11e2141 100644
--- a/Makefile
+++ b/Makefile
@@ -42,7 +42,7 @@ benchjs:
 	node js/bench.js ${BENCHINP}
 
 HTML_OBJ=$(SRCDIR)/html/html.o $(SRCDIR)/html/houdini_href_e.o $(SRCDIR)/html/houdini_html_e.o $(SRCDIR)/html/houdini_html_u.o
-STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o
+STMD_OBJ=$(SRCDIR)/inlines.o $(SRCDIR)/buffer.o $(SRCDIR)/blocks.o $(SRCDIR)/scanners.c $(SRCDIR)/print.o $(SRCDIR)/utf8.o $(SRCDIR)/references.c
 
 $(PROG): $(SRCDIR)/html/html_unescape.h $(SRCDIR)/case_fold_switch.inc $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c
 	$(CC) $(LDFLAGS) -o $@ $(HTML_OBJ) $(STMD_OBJ) $(SRCDIR)/main.c
diff --git a/src/blocks.c b/src/blocks.c
index 72b2dc2..30a8284 100644
--- a/src/blocks.c
+++ b/src/blocks.c
@@ -8,7 +8,6 @@
 #include "utf8.h"
 #include "html/houdini.h"
 #include "scanners.h"
-#include "uthash.h"
 
 #define peek_at(i, n) (i)->data[n]
 
@@ -36,12 +35,7 @@ static node_block* make_block(int tag, int start_line, int start_column)
 extern node_block* make_document()
 {
 	node_block *e = make_block(BLOCK_DOCUMENT, 1, 1);
-	reference *map = NULL;
-	reference ** refmap;
-
-	refmap = (reference**) malloc(sizeof(reference*));
-	*refmap = map;
-	e->as.document.refmap = refmap;
+	e->as.document.refmap = reference_map_new();
 	e->top = e;
 
 	return e;
@@ -164,7 +158,7 @@ static void finalize(node_block* b, int line_number)
 		case BLOCK_PARAGRAPH:
 			pos = 0;
 			while (strbuf_at(&b->string_content, 0) == '[' &&
-					(pos = parse_reference(&b->string_content, b->top->as.document.refmap))) {
+					(pos = parse_reference_inline(&b->string_content, b->top->as.document.refmap))) {
 
 				strbuf_drop(&b->string_content, pos);
 			}
@@ -192,7 +186,7 @@ static void finalize(node_block* b, int line_number)
 			strbuf_drop(&b->string_content, firstlinelen + 1);
 
 			strbuf_trim(&b->as.code.info);
-			unescape_buffer(&b->as.code.info);
+			strbuf_unescape(&b->as.code.info);
 			break;
 
 		case BLOCK_LIST: // determine tight/loose status
@@ -268,7 +262,7 @@ extern void free_blocks(node_block* e)
 		if (e->tag == BLOCK_FENCED_CODE) {
 			strbuf_free(&e->as.code.info);
 		} else if (e->tag == BLOCK_DOCUMENT) {
-			free_reference_map(e->as.document.refmap);
+			reference_map_free(e->as.document.refmap);
 		}
 		free_blocks(e->children);
 		free(e);
@@ -278,7 +272,7 @@ extern void free_blocks(node_block* e)
 
 // Walk through node_block and all children, recursively, parsing
 // string content into inline content where appropriate.
-void process_inlines(node_block* cur, reference** refmap)
+void process_inlines(node_block* cur, reference_map *refmap)
 {
 	switch (cur->tag) {
 		case BLOCK_PARAGRAPH:
diff --git a/src/buffer.c b/src/buffer.c
index 90c2186..cdf8ca0 100644
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -308,3 +308,46 @@ void strbuf_trim(strbuf *buf)
 
 	buf->ptr[buf->size] = '\0';
 }
+
+// Destructively modify string, collapsing consecutive
+// space and newline characters into a single space.
+void strbuf_normalize_whitespace(strbuf *s)
+{
+	bool last_char_was_space = false;
+	int r, w;
+
+	for (r = 0, w = 0; r < s->size; ++r) {
+		switch (s->ptr[r]) {
+		case ' ':
+		case '\n':
+			if (last_char_was_space)
+				break;
+
+			s->ptr[w++] = ' ';
+			last_char_was_space = true;
+			break;
+
+		default:
+			s->ptr[w++] = s->ptr[r];
+			last_char_was_space = false;
+		}
+	}
+
+	strbuf_truncate(s, w);
+}
+
+// Destructively unescape a string: remove backslashes before punctuation chars.
+extern void strbuf_unescape(strbuf *buf)
+{
+	int r, w;
+
+	for (r = 0, w = 0; r < buf->size; ++r) {
+		if (buf->ptr[r] == '\\' && ispunct(buf->ptr[r + 1]))
+			continue;
+
+		buf->ptr[w++] = buf->ptr[r];
+	}
+
+	strbuf_truncate(buf, w);
+}
+
diff --git a/src/buffer.h b/src/buffer.h
index 6f45cbb..1bc1eee 100644
--- a/src/buffer.h
+++ b/src/buffer.h
@@ -108,5 +108,7 @@ int strbuf_strrchr(const strbuf *buf, int c, int pos);
 void strbuf_drop(strbuf *buf, int n);
 void strbuf_truncate(strbuf *buf, int len);
 void strbuf_trim(strbuf *buf);
+void strbuf_normalize_whitespace(strbuf *s);
+void strbuf_unescape(strbuf *s);
 
 #endif
diff --git a/src/inlines.c b/src/inlines.c
index aa0e13e..3040f09 100644
--- a/src/inlines.c
+++ b/src/inlines.c
@@ -7,110 +7,23 @@
 #include "stmd.h"
 #include "html/houdini.h"
 #include "utf8.h"
-#include "uthash.h"
 #include "scanners.h"
 
 typedef struct Subject {
 	chunk input;
 	int pos;
-	int            label_nestlevel;
-	reference**    reference_map;
+	int label_nestlevel;
+	reference_map *refmap;
 } subject;
 
-reference* lookup_reference(reference** refmap, chunk *label);
-reference* make_reference(chunk *label, chunk *url, chunk *title);
-
-static unsigned char *clean_url(chunk *url);
-static unsigned char *clean_title(chunk *title);
-static unsigned char *clean_autolink(chunk *url, int is_email);
-
-inline static void chunk_free(chunk *c);
-inline static void chunk_trim(chunk *c);
-
-inline static chunk chunk_literal(const char *data);
-inline static chunk chunk_buf_detach(strbuf *buf);
-inline static chunk chunk_dup(const chunk *ch, int pos, int len);
-
-static node_inl *parse_chunk_inlines(chunk *chunk, reference** refmap);
+static node_inl *parse_chunk_inlines(chunk *chunk, reference_map *refmap);
 static node_inl *parse_inlines_while(subject* subj, int (*f)(subject*));
 static int parse_inline(subject* subj, node_inl ** last);
 
-static void subject_from_chunk(subject *e, chunk *chunk, reference** refmap);
-static void subject_from_buf(subject *e, strbuf *buffer, reference** refmap);
+static void subject_from_chunk(subject *e, chunk *chunk, reference_map *refmap);
+static void subject_from_buf(subject *e, strbuf *buffer, reference_map *refmap);
 static int subject_find_special_char(subject *subj);
 
-static void normalize_whitespace(strbuf *s);
-
-extern void free_reference(reference *ref) {
-	free(ref->label);
-	free(ref->url);
-	free(ref->title);
-	free(ref);
-}
-
-extern void free_reference_map(reference **refmap) {
-	/* free the hash table contents */
-	reference *s;
-	reference *tmp;
-	if (refmap != NULL) {
-		HASH_ITER(hh, *refmap, s, tmp) {
-			HASH_DEL(*refmap, s);
-			free_reference(s);
-		}
-		free(refmap);
-	}
-}
-
-// normalize reference:  collapse internal whitespace to single space,
-// remove leading/trailing whitespace, case fold
-static unsigned char *normalize_reference(chunk *ref)
-{
-	strbuf normalized = GH_BUF_INIT;
-
-	utf8proc_case_fold(&normalized, ref->data, ref->len);
-	strbuf_trim(&normalized);
-	normalize_whitespace(&normalized);
-
-	return strbuf_detach(&normalized);
-}
-
-// Returns reference if refmap contains a reference with matching
-// label, otherwise NULL.
-extern reference* lookup_reference(reference** refmap, chunk *label)
-{
-	reference *ref = NULL;
-	unsigned char *norm = normalize_reference(label);
-	if (refmap != NULL) {
-		HASH_FIND_STR(*refmap, (char*)norm, ref);
-	}
-	free(norm);
-	return ref;
-}
-
-extern reference* make_reference(chunk *label, chunk *url, chunk *title)
-{
-	reference *ref;
-	ref = malloc(sizeof(reference));
-	ref->label = normalize_reference(label);
-	ref->url = clean_url(url);
-	ref->title = clean_title(title);
-	return ref;
-}
-
-extern void add_reference(reference** refmap, reference* ref)
-{
-	reference * t = NULL;
-	const char *label = (const char *)ref->label;
-
-	HASH_FIND(hh, *refmap, label, strlen(label), t);
-
-	if (t == NULL) {
-		HASH_ADD_KEYPTR(hh, *refmap, label, strlen(label), ref);
-	} else {
-		free_reference(ref);  // we free this now since it won't be in the refmap
-	}
-}
-
 static unsigned char *bufdup(const unsigned char *buf)
 {
 	unsigned char *new = NULL;
@@ -236,26 +149,26 @@ inline static node_inl* append_inlines(node_inl* a, node_inl* b)
 	return a;
 }
 
-static void subject_from_buf(subject *e, strbuf *buffer, reference** refmap)
+static void subject_from_buf(subject *e, strbuf *buffer, reference_map *refmap)
 {
 	e->input.data = buffer->ptr;
 	e->input.len = buffer->size;
 	e->input.alloc = 0;
 	e->pos = 0;
 	e->label_nestlevel = 0;
-	e->reference_map = refmap;
+	e->refmap = refmap;
 
 	chunk_rtrim(&e->input);
 }
 
-static void subject_from_chunk(subject *e, chunk *chunk, reference** refmap)
+static void subject_from_chunk(subject *e, chunk *chunk, reference_map *refmap)
 {
 	e->input.data = chunk->data;
 	e->input.len = chunk->len;
 	e->input.alloc = 0;
 	e->pos = 0;
 	e->label_nestlevel = 0;
-	e->reference_map = refmap;
+	e->refmap = refmap;
 
 	chunk_rtrim(&e->input);
 }
@@ -325,33 +238,6 @@ static int scan_to_closing_backticks(subject* subj, int openticklength)
 	return (subj->pos);
 }
 
-// Destructively modify string, collapsing consecutive
-// space and newline characters into a single space.
-static void normalize_whitespace(strbuf *s)
-{
-	bool last_char_was_space = false;
-	int r, w;
-
-	for (r = 0, w = 0; r < s->size; ++r) {
-		switch (s->ptr[r]) {
-		case ' ':
-		case '\n':
-			if (last_char_was_space)
-				break;
-
-			s->ptr[w++] = ' ';
-			last_char_was_space = true;
-			break;
-
-		default:
-			s->ptr[w++] = s->ptr[r];
-			last_char_was_space = false;
-		}
-	}
-
-	strbuf_truncate(s, w);
-}
-
 // Parse backtick code section or raw backticks, return an inline.
 // Assumes that the subject has a backtick at the current position.
 static node_inl* handle_backticks(subject *subj)
@@ -368,7 +254,7 @@ static node_inl* handle_backticks(subject *subj)
 
 		strbuf_set(&buf, subj->input.data + startpos, endpos - startpos - openticks.len);
 		strbuf_trim(&buf);
-		normalize_whitespace(&buf);
+		strbuf_normalize_whitespace(&buf);
 
 		return make_code(chunk_buf_detach(&buf));
 	}
@@ -575,24 +461,9 @@ static node_inl *make_str_with_entities(chunk *content)
 	}
 }
 
-// Destructively unescape a string: remove backslashes before punctuation chars.
-extern void unescape_buffer(strbuf *buf)
-{
-	int r, w;
-
-	for (r = 0, w = 0; r < buf->size; ++r) {
-		if (buf->ptr[r] == '\\' && ispunct(buf->ptr[r + 1]))
-			continue;
-
-		buf->ptr[w++] = buf->ptr[r];
-	}
-
-	strbuf_truncate(buf, w);
-}
-
 // Clean a URL: remove surrounding whitespace and surrounding <>,
 // and remove \ that escape punctuation.
-static unsigned char *clean_url(chunk *url)
+unsigned char *clean_url(chunk *url)
 {
 	strbuf buf = GH_BUF_INIT;
 
@@ -607,11 +478,11 @@ static unsigned char *clean_url(chunk *url)
 		houdini_unescape_html_f(&buf, url->data, url->len);
 	}
 
-	unescape_buffer(&buf);
+	strbuf_unescape(&buf);
 	return strbuf_detach(&buf);
 }
 
-static unsigned char *clean_autolink(chunk *url, int is_email)
+unsigned char *clean_autolink(chunk *url, int is_email)
 {
 	strbuf buf = GH_BUF_INIT;
 
@@ -628,7 +499,7 @@ static unsigned char *clean_autolink(chunk *url, int is_email)
 }
 
 // Clean a title: remove surrounding quotes and remove \ that escape punctuation.
-static unsigned char *clean_title(chunk *title)
+unsigned char *clean_title(chunk *title)
 {
 	strbuf buf = GH_BUF_INIT;
 	unsigned char first, last;
@@ -648,7 +519,7 @@ static unsigned char *clean_title(chunk *title)
 		houdini_unescape_html_f(&buf, title->data, title->len);
 	}
 
-	unescape_buffer(&buf);
+	strbuf_unescape(&buf);
 	return strbuf_detach(&buf);
 }
 
@@ -810,7 +681,7 @@ static node_inl* handle_left_bracket(subject* subj)
 			} else {
 				// if we get here, we matched a label but didn't get further:
 				subj->pos = endlabel;
-				lab = parse_chunk_inlines(&rawlabel, subj->reference_map);
+				lab = parse_chunk_inlines(&rawlabel, subj->refmap);
 				result = append_inlines(make_str(chunk_literal("[")),
 						append_inlines(lab,
 							make_str(chunk_literal("]"))));
@@ -834,13 +705,13 @@ static node_inl* handle_left_bracket(subject* subj)
 			}
 
 			// lookup rawlabel in subject->reference_map:
-			ref = lookup_reference(subj->reference_map, &reflabel);
+			ref = reference_lookup(subj->refmap, &reflabel);
 			if (ref != NULL) { // found
 				lab = parse_chunk_inlines(&rawlabel, NULL);
 				result = make_ref_link(lab, ref);
 			} else {
 				subj->pos = endlabel;
-				lab = parse_chunk_inlines(&rawlabel, subj->reference_map);
+				lab = parse_chunk_inlines(&rawlabel, subj->refmap);
 				result = append_inlines(make_str(chunk_literal("[")),
 						append_inlines(lab, make_str(chunk_literal("]"))));
 			}
@@ -887,7 +758,7 @@ extern node_inl* parse_inlines_while(subject* subj, int (*f)(subject*))
 	return result;
 }
 
-node_inl *parse_chunk_inlines(chunk *chunk, reference** refmap)
+node_inl *parse_chunk_inlines(chunk *chunk, reference_map *refmap)
 {
 	subject subj;
 	subject_from_chunk(&subj, chunk, refmap);
@@ -987,7 +858,7 @@ static int parse_inline(subject* subj, node_inl ** last)
 	return 1;
 }
 
-extern node_inl* parse_inlines(strbuf *input, reference** refmap)
+extern node_inl* parse_inlines(strbuf *input, reference_map *refmap)
 {
 	subject subj;
 	subject_from_buf(&subj, input, refmap);
@@ -1009,7 +880,7 @@ void spnl(subject* subj)
 // Modify refmap if a reference is encountered.
 // Return 0 if no reference found, otherwise position of subject
 // after reference is parsed.
-extern int parse_reference(strbuf *input, reference** refmap)
+int parse_reference_inline(strbuf *input, reference_map *refmap)
 {
 	subject subj;
 
@@ -1019,7 +890,6 @@ extern int parse_reference(strbuf *input, reference** refmap)
 
 	int matchlen = 0;
 	int beforetitle;
-	reference *new = NULL;
 
 	subject_from_buf(&subj, input, NULL);
 
@@ -1065,9 +935,7 @@ extern int parse_reference(strbuf *input, reference** refmap)
 		return 0;
 	}
 	// insert reference into refmap
-	new = make_reference(&lab, &url, &title);
-	add_reference(refmap, new);
-
+	reference_create(refmap, &lab, &url, &title);
 	return subj.pos;
 }
 
diff --git a/src/references.c b/src/references.c
new file mode 100644
index 0000000..ff64b00
--- /dev/null
+++ b/src/references.c
@@ -0,0 +1,109 @@
+#include "stmd.h"
+#include "utf8.h"
+#include "references.h"
+
+static unsigned int
+refhash(const unsigned char *link_ref)
+{
+	unsigned int hash = 0;
+
+	while (*link_ref)
+		hash = (*link_ref++) + (hash << 6) + (hash << 16) - hash;
+
+	return hash;
+}
+
+// normalize reference:  collapse internal whitespace to single space,
+// remove leading/trailing whitespace, case fold
+static unsigned char *normalize_reference(chunk *ref)
+{
+	strbuf normalized = GH_BUF_INIT;
+
+	utf8proc_case_fold(&normalized, ref->data, ref->len);
+	strbuf_trim(&normalized);
+	strbuf_normalize_whitespace(&normalized);
+
+	return strbuf_detach(&normalized);
+}
+
+static void add_reference(reference_map *map, reference* ref)
+{
+	ref->next = map->table[ref->hash % REFMAP_SIZE];
+	map->table[ref->hash % REFMAP_SIZE] = ref;
+}
+
+extern reference *reference_create(reference_map *map, chunk *label, chunk *url, chunk *title)
+{
+	reference *ref;
+	ref = malloc(sizeof(reference));
+	ref->label = normalize_reference(label);
+	ref->hash = refhash(ref->label);
+	ref->url = clean_url(url);
+	ref->title = clean_title(title);
+	ref->next = NULL;
+
+	add_reference(map, ref);
+
+	return ref;
+}
+
+// Returns reference if refmap contains a reference with matching
+// label, otherwise NULL.
+reference* reference_lookup(reference_map *map, chunk *label)
+{
+	reference *ref = NULL;
+	unsigned char *norm;
+	unsigned int hash;
+	
+	if (map == NULL)
+		return NULL;
+	
+	norm = normalize_reference(label);
+	hash = refhash(norm);
+	ref = map->table[hash % REFMAP_SIZE];
+
+	while (ref) {
+		if (ref->label[0] == norm[0] &&
+			!strcmp((char *)ref->label, (char *)norm))
+			break;
+		ref = ref->next;
+	}
+
+	free(norm);
+	return ref;
+}
+
+static void reference_free(reference *ref)
+{
+	free(ref->label);
+	free(ref->url);
+	free(ref->title);
+	free(ref);
+}
+
+void reference_map_free(reference_map *map)
+{
+	unsigned int i;
+
+	for (i = 0; i < REFMAP_SIZE; ++i) {
+		reference *ref = map->table[i];
+		reference *next;
+
+		while (ref) {
+			next = ref->next;
+			reference_free(ref);
+			ref = next;
+		}
+	}
+
+	free(map->table);
+	free(map);
+}
+
+reference_map *reference_map_new(void)
+{
+	reference_map *map = malloc(sizeof(reference_map));
+	memset(map, 0x0, sizeof(reference_map));
+	return map;
+}
+
diff --git a/src/references.h b/src/references.h
new file mode 100644
index 0000000..78fffe7
--- /dev/null
+++ b/src/references.h
@@ -0,0 +1,27 @@
+#ifndef _REFERENCES_H_
+#define _REFERENCES_H_
+
+#define REFMAP_SIZE 16
+
+struct reference {
+	struct reference *next;
+	unsigned char *label;
+	unsigned char *url;
+	unsigned char *title;
+	unsigned int hash;
+};
+
+typedef struct reference reference;
+
+struct reference_map {
+	reference *table[REFMAP_SIZE];
+};
+
+typedef struct reference_map reference_map;
+
+reference_map *reference_map_new(void);
+void reference_map_free(reference_map *map);
+reference* reference_lookup(reference_map *map, chunk *label);
+extern reference *reference_create(reference_map *map, chunk *label, chunk *url, chunk *title);
+
+#endif
diff --git a/src/stmd.h b/src/stmd.h
index 21a86b0..4e21e6c 100644
--- a/src/stmd.h
+++ b/src/stmd.h
@@ -5,7 +5,7 @@
 #include <stdio.h>
 #include "buffer.h"
 #include "chunk.h"
-#include "uthash.h"
+#include "references.h"
 
 #define VERSION "0.1"
 #define CODE_INDENT 4
@@ -36,17 +36,7 @@ struct node_inl {
 
 typedef struct node_inl node_inl;
 
-struct reference {
-  unsigned char *label;
-  unsigned char *url;
-  unsigned char *title;
-  UT_hash_handle  hh; // used by uthash
-};
-
-typedef struct reference reference;
-
 // Types for blocks
-
 struct ListData {
 	enum {
 		bullet,
@@ -104,7 +94,7 @@ struct node_block {
 			int level;
 		} header;
 		struct {
-			reference** refmap;
+			reference_map *refmap;
 		} document;
 	} as;
 
@@ -114,14 +104,10 @@ struct node_block {
 
 typedef struct node_block node_block;
 
-node_inl* parse_inlines(strbuf *input, reference** refmap);
+node_inl* parse_inlines(strbuf *input, reference_map *refmap);
 void free_inlines(node_inl* e);
 
-int parse_reference(strbuf *input, reference** refmap);
-void free_reference(reference *ref);
-void free_reference_map(reference **refmap);
-
-void add_reference(reference** refmap, reference* ref);
+int parse_reference_inline(strbuf *input, reference_map *refmap);
 void unescape_buffer(strbuf *buf);
 
 extern node_block* make_document();
@@ -138,4 +124,8 @@ void print_blocks(node_block* blk, int indent);
 void blocks_to_html(strbuf *html, node_block *b, bool tight);
 void inlines_to_html(strbuf *html, node_inl *b);
 
+unsigned char *clean_url(chunk *url);
+unsigned char *clean_autolink(chunk *url, int is_email);
+unsigned char *clean_title(chunk *title);
+
 #endif
diff --git a/src/utf8.c b/src/utf8.c
index 12d7ba5..c65aec6 100644
--- a/src/utf8.c
+++ b/src/utf8.c
@@ -25,7 +25,7 @@ static const int8_t utf8proc_utf8class[256] = {
 
 static void encode_unknown(strbuf *buf)
 {
-	static const unsigned char repl[] = {239, 191, 189};
+	static const uint8_t repl[] = {239, 191, 189};
 	strbuf_put(buf, repl, 3);
 }
 
@@ -52,9 +52,9 @@ ssize_t utf8proc_charlen(const uint8_t *str, ssize_t str_len)
 	return length;
 }
 
-void utf8proc_detab(strbuf *ob, const unsigned char *line, size_t size)
+void utf8proc_detab(strbuf *ob, const uint8_t *line, size_t size)
 {
-	static const unsigned char whitespace[] = "    ";
+	static const uint8_t whitespace[] = "    ";
 
 	size_t i = 0, tab = 0;
 
@@ -132,7 +132,7 @@ ssize_t utf8proc_iterate(const uint8_t *str, ssize_t str_len, int32_t *dst)
 
 void utf8proc_encode_char(int32_t uc, strbuf *buf)
 {
-	unsigned char dst[4];
+	uint8_t dst[4];
 	int len = 0;
 
 	assert(uc >= 0);
@@ -169,7 +169,7 @@ void utf8proc_encode_char(int32_t uc, strbuf *buf)
 	strbuf_put(buf, dst, len);
 }
 
-void utf8proc_case_fold(strbuf *dest, const unsigned char *str, int len)
+void utf8proc_case_fold(strbuf *dest, const uint8_t *str, int len)
 {
 	int32_t c;
 
diff --git a/src/utf8.h b/src/utf8.h
index 1e4e556..9506b75 100644
--- a/src/utf8.h
+++ b/src/utf8.h
@@ -1,12 +1,13 @@
 #ifndef _H_STMD_UTF8_
 #define _H_STMD_UTF8_
 
+#include <stdint.h>
 #include "buffer.h"
 
-void utf8proc_case_fold(strbuf *dest, const unsigned char *str, int len);
+void utf8proc_case_fold(strbuf *dest, const uint8_t *str, int len);
 void utf8proc_encode_char(int32_t uc, strbuf *buf);
 ssize_t utf8proc_iterate(const uint8_t *str, ssize_t str_len, int32_t *dst);
 ssize_t utf8proc_charlen(const uint8_t *str, ssize_t str_len);
-void utf8proc_detab(strbuf *dest, const unsigned char *line, size_t size);
+void utf8proc_detab(strbuf *dest, const uint8_t *line, size_t size);
 
 #endif