add line length and make it utf-8 compatible

diff --git a/include/markdown.h b/include/markdown.h
index b26765e..dc759e0 100644 (file)
--- a/include/markdown.h
+++ b/include/markdown.h
@@ -23,6 +23,7 @@ typedef struct _line_t {
     struct _line_t *prev;
     struct _line_t *next;
     int bits;
+    int length;
     int offset;
 } line_t;
 

diff --git a/include/parser.h b/include/parser.h
index 7ade17c..091c3d5 100644 (file)
--- a/include/parser.h
+++ b/include/parser.h
@@ -6,6 +6,7 @@
 document_t *markdown_load(FILE *input);
 int markdown_analyse(cstring_t *text);
 int is_utf8(char ch);
+int length_utf8(char ch);
 int next_nonblank(cstring_t *text, int i);
 int next_blank(cstring_t *text, int i);
 

diff --git a/markdown.c b/markdown.c
index 90219e5..0d42005 100644 (file)
--- a/markdown.c
+++ b/markdown.c
@@ -8,7 +8,7 @@ line_t *new_line() {
     line_t *x = malloc(sizeof(line_t));
     x->text = (void*)0;
     x->prev = x->next = (void*)0;
-    x->bits = x->offset = 0;
+    x->bits = x->length = x->offset = 0;
     return x;
 }
 

diff --git a/parser.c b/parser.c
index 0343509..fddd8d8 100644 (file)
--- a/parser.c
+++ b/parser.c
@@ -5,7 +5,7 @@
 
 document_t *markdown_load(FILE *input) {
 
-    int c = 0, i = 0, bits = 0;
+    int c = 0, i = 0, l = 0, bits = 0;
 
     document_t *doc;
     page_t *page;
@@ -29,6 +29,10 @@ document_t *markdown_load(FILE *input) {
 
                 // clear text
                 (text->reset)(text);
+
+                // reset line length
+                l = 0;
+
                 // create next page
                 page = next_page(page);
 
@@ -54,23 +58,48 @@ document_t *markdown_load(FILE *input) {
                 // add bits to line
                 line->bits = bits;
 
+                // add length to line
+                line->length = l;
+
                 // calc offset
                 line->offset = next_nonblank(text, 0);
 
                 // new text
                 text = cstring_init();
+
+                // reset line length
+                l = 0;
             }
 
         } else if(c == '\t') {
 
             // expand tab to spaces
-            for (i = 0;  i <= 4;  i++)
+            for (i = 0;  i <= 4;  i++) {
                 (text->expand)(text, ' ');
+                l++;
+            }
 
-        } else if(isprint(c) || isspace(c) || is_utf8(c)) {
+        } else if(isprint(c) || isspace(c)) {
 
             // add char to line
             (text->expand)(text, c);
+
+            // increase line lenght
+            l++;
+
+        } else if(is_utf8(c)) {
+
+            // add char to line
+            (text->expand)(text, c);
+
+            // if utf-8 char > 1 byte add remaing to line
+            for(i = 0; i < length_utf8(c) - 1; i++) {
+                c = fgetc(input);
+                (text->expand)(text, c);
+            }
+
+            // increase line length
+            l++;
         }
     }
 
@@ -207,6 +236,15 @@ int is_utf8(char ch) {
     return (ch & 0x80);
 }
 
+int length_utf8(char ch) {
+    int i = 0;
+    while(ch & 0x80) {
+        i++;
+        ch <<= 1;
+    }
+    return i;
+}
+
 int next_nonblank(cstring_t *text, int i) {
     while ((i < text->size) && isspace((text->text)[i]))
         ++i;

diff --git a/tmp.c b/tmp.c
index eeec4a4..33b8603 100644 (file)
--- a/tmp.c
+++ b/tmp.c
@@ -69,7 +69,7 @@ int main(int argc, char *argv[]) {
         if(doc->header) {
             header = doc->header;
             while(header &&
-                header->text->size > 0 &&
+                header->length > 0 &&
                 header->text->text[0] == '%') {
 
                 offset = next_blank(header->text, 0) + 1;
@@ -92,7 +92,7 @@ int main(int argc, char *argv[]) {
             while(line) {
                 cl++;
                 if(debug > 1) {
-                    fprintf(stderr, "  line %i: bits = %i, length = %i\n", cl, line->bits, line->text->size);
+                    fprintf(stderr, "  line %i: bits = %i, length = %i\n", cl, line->bits, line->length);
                 }
                 line = line->next;
             }