smu.c: Format source code
This commit is contained in:
parent
82048dd49e
commit
c702617acd
1 changed files with 273 additions and 237 deletions
240
smu.c
240
smu.c
|
@ -10,7 +10,13 @@
|
|||
#include <ctype.h>
|
||||
|
||||
#define LENGTH(x) sizeof(x) / sizeof(x[0])
|
||||
#define ADDC(b,i) if(i % BUFSIZ == 0) { b = realloc(b, (i + BUFSIZ) * sizeof(char)); if(!b) eprint("Malloc failed."); } b[i]
|
||||
#define ADDC(b, i) \
|
||||
if (i % BUFSIZ == 0) { \
|
||||
b = realloc(b, (i + BUFSIZ) * sizeof(char)); \
|
||||
if (!b) \
|
||||
eprint("Malloc failed."); \
|
||||
} \
|
||||
b[i]
|
||||
|
||||
typedef int (*Parser)(const char *, const char *, int);
|
||||
typedef struct {
|
||||
|
@ -19,26 +25,40 @@ typedef struct {
|
|||
char *before, *after;
|
||||
} Tag;
|
||||
|
||||
static int doamp(const char *begin, const char *end, int newblock); /* Parser for & */
|
||||
static int docomment(const char *begin, const char *end, int newblock); /* Parser for html-comments */
|
||||
static int dogtlt(const char *begin, const char *end, int newblock); /* Parser for < and > */
|
||||
static int dohtml(const char *begin, const char *end, int newblock); /* Parser for html */
|
||||
static int dolineprefix(const char *begin, const char *end, int newblock);/* Parser for line prefix tags */
|
||||
static int dolink(const char *begin, const char *end, int newblock); /* Parser for links and images */
|
||||
static int dolist(const char *begin, const char *end, int newblock); /* Parser for lists */
|
||||
static int doparagraph(const char *begin, const char *end, int newblock); /* Parser for paragraphs */
|
||||
static int doreplace(const char *begin, const char *end, int newblock); /* Parser for simple replaces */
|
||||
static int doshortlink(const char *begin, const char *end, int newblock); /* Parser for links and images */
|
||||
static int dosurround(const char *begin, const char *end, int newblock); /* Parser for surrounding tags */
|
||||
static int dounderline(const char *begin, const char *end, int newblock); /* Parser for underline tags */
|
||||
static int doamp(const char *begin, const char *end,
|
||||
int newblock); /* Parser for & */
|
||||
static int docomment(const char *begin, const char *end,
|
||||
int newblock); /* Parser for html-comments */
|
||||
static int dogtlt(const char *begin, const char *end,
|
||||
int newblock); /* Parser for < and > */
|
||||
static int dohtml(const char *begin, const char *end,
|
||||
int newblock); /* Parser for html */
|
||||
static int dolineprefix(const char *begin, const char *end,
|
||||
int newblock); /* Parser for line prefix tags */
|
||||
static int dolink(const char *begin, const char *end,
|
||||
int newblock); /* Parser for links and images */
|
||||
static int dolist(const char *begin, const char *end,
|
||||
int newblock); /* Parser for lists */
|
||||
static int doparagraph(const char *begin, const char *end,
|
||||
int newblock); /* Parser for paragraphs */
|
||||
static int doreplace(const char *begin, const char *end,
|
||||
int newblock); /* Parser for simple replaces */
|
||||
static int doshortlink(const char *begin, const char *end,
|
||||
int newblock); /* Parser for links and images */
|
||||
static int dosurround(const char *begin, const char *end,
|
||||
int newblock); /* Parser for surrounding tags */
|
||||
static int dounderline(const char *begin, const char *end,
|
||||
int newblock); /* Parser for underline tags */
|
||||
static void *ereallocz(void *p, size_t size);
|
||||
static void eprint(const char *format, ...);
|
||||
static void hprint(const char *begin, const char *end); /* escapes HTML and prints it to output */
|
||||
static void process(const char *begin, const char *end, int isblock); /* Processes range between begin and end. */
|
||||
static void hprint(const char *begin,
|
||||
const char *end); /* escapes HTML and prints it to output */
|
||||
static void process(const char *begin, const char *end,
|
||||
int isblock); /* Processes range between begin and end. */
|
||||
|
||||
/* list of parsers */
|
||||
static Parser parsers[] = { dounderline, docomment, dolineprefix,
|
||||
dolist, doparagraph, dogtlt, dosurround, dolink,
|
||||
static Parser parsers[] = { dounderline, docomment, dolineprefix, dolist,
|
||||
doparagraph, dogtlt, dosurround, dolink,
|
||||
doshortlink, dohtml, doamp, doreplace };
|
||||
static int nohtml = 0;
|
||||
|
||||
|
@ -72,29 +92,18 @@ static Tag surround[] = {
|
|||
};
|
||||
|
||||
static const char *replace[][2] = {
|
||||
{ "\\\\", "\\" },
|
||||
{ "\\`", "`" },
|
||||
{ "\\*", "*" },
|
||||
{ "\\_", "_" },
|
||||
{ "\\{", "{" },
|
||||
{ "\\}", "}" },
|
||||
{ "\\[", "[" },
|
||||
{ "\\]", "]" },
|
||||
{ "\\(", "(" },
|
||||
{ "\\)", ")" },
|
||||
{ "\\#", "#" },
|
||||
{ "\\+", "+" },
|
||||
{ "\\-", "-" },
|
||||
{ "\\.", "." },
|
||||
{ "\\!", "!" },
|
||||
{ "\\\\", "\\" }, { "\\`", "`" }, { "\\*", "*" }, { "\\_", "_" },
|
||||
{ "\\{", "{" }, { "\\}", "}" }, { "\\[", "[" }, { "\\]", "]" },
|
||||
{ "\\(", "(" }, { "\\)", ")" }, { "\\#", "#" }, { "\\+", "+" },
|
||||
{ "\\-", "-" }, { "\\.", "." }, { "\\!", "!" },
|
||||
};
|
||||
|
||||
static const char *insert[][2] = {
|
||||
{ " \n", "<br />" },
|
||||
};
|
||||
|
||||
void
|
||||
eprint(const char *format, ...) {
|
||||
void eprint(const char *format, ...)
|
||||
{
|
||||
va_list ap;
|
||||
|
||||
va_start(ap, format);
|
||||
|
@ -103,14 +112,15 @@ eprint(const char *format, ...) {
|
|||
exit(EXIT_FAILURE);
|
||||
}
|
||||
|
||||
int
|
||||
doamp(const char *begin, const char *end, int newblock) {
|
||||
int doamp(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
const char *p;
|
||||
|
||||
if (*begin != '&')
|
||||
return 0;
|
||||
if (!nohtml) {
|
||||
for(p = begin + 1; p != end && !strchr("; \\\n\t", *p); p++);
|
||||
for (p = begin + 1; p != end && !strchr("; \\\n\t", *p); p++)
|
||||
;
|
||||
if (p == end || *p == ';')
|
||||
return 0;
|
||||
}
|
||||
|
@ -118,8 +128,8 @@ doamp(const char *begin, const char *end, int newblock) {
|
|||
return 1;
|
||||
}
|
||||
|
||||
int
|
||||
dogtlt(const char *begin, const char *end, int newblock) {
|
||||
int dogtlt(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
int brpos;
|
||||
char c;
|
||||
|
||||
|
@ -132,16 +142,16 @@ dogtlt(const char *begin, const char *end, int newblock) {
|
|||
if (!brpos && (c < 'a' || c > 'z') && (c < 'A' || c > 'Z')) {
|
||||
fputs("<", stdout);
|
||||
return 1;
|
||||
}
|
||||
else if(brpos && (c < 'a' || c > 'z') && (c < 'A' || c > 'Z') && !strchr("/\"'",c)) {
|
||||
} else if (brpos && (c < 'a' || c > 'z') && (c < 'A' || c > 'Z') &&
|
||||
!strchr("/\"'", c)) {
|
||||
fprintf(stdout, "%c>", c);
|
||||
return 2;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
docomment(const char *begin, const char *end, int newblock) {
|
||||
int docomment(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
char *p;
|
||||
|
||||
if (nohtml || strncmp("<!--", begin, 4))
|
||||
|
@ -153,8 +163,8 @@ docomment(const char *begin, const char *end, int newblock) {
|
|||
return (p + 3 - begin) * (newblock ? -1 : 1);
|
||||
}
|
||||
|
||||
int
|
||||
dohtml(const char *begin, const char *end, int newblock) {
|
||||
int dohtml(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
const char *p, *tag, *tagend;
|
||||
|
||||
if (nohtml || begin + 2 >= end)
|
||||
|
@ -164,15 +174,18 @@ dohtml(const char *begin, const char *end, int newblock) {
|
|||
return 0;
|
||||
p++;
|
||||
tag = p;
|
||||
for(; isalnum(*p) && p < end; p++);
|
||||
for (; isalnum(*p) && p < end; p++)
|
||||
;
|
||||
tagend = p;
|
||||
if (p > end || tag == tagend)
|
||||
return 0;
|
||||
while ((p = strstr(p, "</")) && p < end) {
|
||||
p += 2;
|
||||
if(strncmp(p, tag, tagend - tag) == 0 && p[tagend - tag] == '>') {
|
||||
if (strncmp(p, tag, tagend - tag) == 0 &&
|
||||
p[tagend - tag] == '>') {
|
||||
p++;
|
||||
fwrite(begin, sizeof(char), p - begin + tagend - tag - 1, stdout);
|
||||
fwrite(begin, sizeof(char),
|
||||
p - begin + tagend - tag - 1, stdout);
|
||||
return p - begin + tagend - tag - 1;
|
||||
}
|
||||
}
|
||||
|
@ -180,13 +193,12 @@ dohtml(const char *begin, const char *end, int newblock) {
|
|||
if (p) {
|
||||
fwrite(begin, sizeof(char), p - begin + 1, stdout);
|
||||
return p - begin + 1;
|
||||
}
|
||||
else
|
||||
} else
|
||||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
dolineprefix(const char *begin, const char *end, int newblock) {
|
||||
int dolineprefix(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
unsigned int i, j, l;
|
||||
char *buffer;
|
||||
const char *p;
|
||||
|
@ -216,7 +228,8 @@ dolineprefix(const char *begin, const char *end, int newblock) {
|
|||
|
||||
/* Collect lines into buffer while they start with the prefix */
|
||||
j = 0;
|
||||
while((strncmp(lineprefix[i].search, p, l) == 0) && p + l < end) {
|
||||
while ((strncmp(lineprefix[i].search, p, l) == 0) &&
|
||||
p + l < end) {
|
||||
p += l;
|
||||
|
||||
/* Special case for blockquotes: optional space after > */
|
||||
|
@ -239,7 +252,8 @@ dolineprefix(const char *begin, const char *end, int newblock) {
|
|||
|
||||
ADDC(buffer, j) = '\0';
|
||||
if (lineprefix[i].process)
|
||||
process(buffer, buffer + strlen(buffer), lineprefix[i].process >= 2);
|
||||
process(buffer, buffer + strlen(buffer),
|
||||
lineprefix[i].process >= 2);
|
||||
else
|
||||
hprint(buffer, buffer + strlen(buffer));
|
||||
puts(lineprefix[i].after);
|
||||
|
@ -249,8 +263,8 @@ dolineprefix(const char *begin, const char *end, int newblock) {
|
|||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
dolink(const char *begin, const char *end, int newblock) {
|
||||
int dolink(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
int img, len, sep, parens_depth = 1;
|
||||
const char *desc, *link, *p, *q, *descend, *linkend;
|
||||
const char *title = NULL, *titleend = NULL;
|
||||
|
@ -264,7 +278,8 @@ dolink(const char *begin, const char *end, int newblock) {
|
|||
p = desc = begin + 1 + img;
|
||||
if (!(p = strstr(desc, "](")) || p > end)
|
||||
return 0;
|
||||
for(q = strstr(desc, ") || p > end)
|
||||
return 0;
|
||||
descend = p;
|
||||
|
@ -287,13 +302,16 @@ dolink(const char *begin, const char *end, int newblock) {
|
|||
sep = p[0]; /* separator: can be " or ' */
|
||||
title = p + 1;
|
||||
/* strip trailing whitespace */
|
||||
for(linkend = p; linkend > link && isspace(*(linkend - 1)); linkend--);
|
||||
for(titleend = q - 1; titleend > title && isspace(*(titleend)); titleend--);
|
||||
for (linkend = p; linkend > link && isspace(*(linkend - 1));
|
||||
linkend--)
|
||||
;
|
||||
for (titleend = q - 1; titleend > title && isspace(*(titleend));
|
||||
titleend--)
|
||||
;
|
||||
if (*titleend != sep) {
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
else {
|
||||
} else {
|
||||
linkend = q;
|
||||
}
|
||||
|
||||
|
@ -316,8 +334,7 @@ dolink(const char *begin, const char *end, int newblock) {
|
|||
fputs("\" ", stdout);
|
||||
}
|
||||
fputs("/>", stdout);
|
||||
}
|
||||
else {
|
||||
} else {
|
||||
fputs("<a href=\"", stdout);
|
||||
hprint(link, linkend);
|
||||
fputs("\"", stdout);
|
||||
|
@ -333,8 +350,8 @@ dolink(const char *begin, const char *end, int newblock) {
|
|||
return len;
|
||||
}
|
||||
|
||||
int
|
||||
dolist(const char *begin, const char *end, int newblock) {
|
||||
int dolist(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
unsigned int i, j, indent, run, ul, isblock;
|
||||
const char *p, *q;
|
||||
char *buffer = NULL;
|
||||
|
@ -353,14 +370,16 @@ dolist(const char *begin, const char *end, int newblock) {
|
|||
marker = *p;
|
||||
} else {
|
||||
ul = 0;
|
||||
for(; p < end && *p >= '0' && *p <= '9'; p++);
|
||||
for (; p < end && *p >= '0' && *p <= '9'; p++)
|
||||
;
|
||||
if (p >= end || *p != '.')
|
||||
return 0;
|
||||
}
|
||||
p++;
|
||||
if (p >= end || !(*p == ' ' || *p == '\t'))
|
||||
return 0;
|
||||
for(p++; p != end && (*p == ' ' || *p == '\t'); p++);
|
||||
for (p++; p != end && (*p == ' ' || *p == '\t'); p++)
|
||||
;
|
||||
indent = p - q;
|
||||
buffer = ereallocz(buffer, BUFSIZ);
|
||||
if (!newblock)
|
||||
|
@ -374,7 +393,11 @@ dolist(const char *begin, const char *end, int newblock) {
|
|||
break;
|
||||
else {
|
||||
/* Handle empty lines */
|
||||
for(q = p + 1; (*q == ' ' || *q == '\t') && q < end; q++);
|
||||
for (q = p + 1;
|
||||
(*q == ' ' || *q == '\t') &&
|
||||
q < end;
|
||||
q++)
|
||||
;
|
||||
if (*q == '\n') {
|
||||
ADDC(buffer, i) = '\n';
|
||||
i++;
|
||||
|
@ -388,7 +411,10 @@ dolist(const char *begin, const char *end, int newblock) {
|
|||
if (ul && *q == marker)
|
||||
j = 1;
|
||||
else if (!ul) {
|
||||
for(; q + j != end && q[j] >= '0' && q[j] <= '9' && j < indent; j++);
|
||||
for (; q + j != end && q[j] >= '0' &&
|
||||
q[j] <= '9' && j < indent;
|
||||
j++)
|
||||
;
|
||||
if (q + j == end)
|
||||
break;
|
||||
if (j > 0 && q[j] == '.')
|
||||
|
@ -397,7 +423,10 @@ dolist(const char *begin, const char *end, int newblock) {
|
|||
j = 0;
|
||||
}
|
||||
if (q + indent < end)
|
||||
for(; (q[j] == ' ' || q[j] == '\t') && j < indent; j++);
|
||||
for (; (q[j] == ' ' || q[j] == '\t') &&
|
||||
j < indent;
|
||||
j++)
|
||||
;
|
||||
if (j == indent) {
|
||||
ADDC(buffer, i) = '\n';
|
||||
i++;
|
||||
|
@ -407,26 +436,27 @@ dolist(const char *begin, const char *end, int newblock) {
|
|||
p++;
|
||||
else
|
||||
break;
|
||||
}
|
||||
else if (j < indent)
|
||||
} else if (j < indent)
|
||||
run = 0;
|
||||
}
|
||||
ADDC(buffer, i) = *p;
|
||||
}
|
||||
ADDC(buffer, i) = '\0';
|
||||
fputs("<li>", stdout);
|
||||
process(buffer, buffer + i, isblock > 1 || (isblock == 1 && run));
|
||||
process(buffer, buffer + i,
|
||||
isblock > 1 || (isblock == 1 && run));
|
||||
fputs("</li>\n", stdout);
|
||||
}
|
||||
fputs(ul ? "</ul>\n" : "</ol>\n", stdout);
|
||||
free(buffer);
|
||||
p--;
|
||||
while(*(--p) == '\n');
|
||||
while (*(--p) == '\n')
|
||||
;
|
||||
return -(p - begin + 1);
|
||||
}
|
||||
|
||||
int
|
||||
doparagraph(const char *begin, const char *end, int newblock) {
|
||||
int doparagraph(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
const char *p;
|
||||
|
||||
if (!newblock)
|
||||
|
@ -442,8 +472,8 @@ doparagraph(const char *begin, const char *end, int newblock) {
|
|||
return -(p - begin);
|
||||
}
|
||||
|
||||
int
|
||||
doreplace(const char *begin, const char *end, int newblock) {
|
||||
int doreplace(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
unsigned int i, l;
|
||||
|
||||
for (i = 0; i < LENGTH(insert); i++)
|
||||
|
@ -461,8 +491,8 @@ doreplace(const char *begin, const char *end, int newblock) {
|
|||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
doshortlink(const char *begin, const char *end, int newblock) {
|
||||
int doshortlink(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
const char *p, *c;
|
||||
int ismail = 0;
|
||||
|
||||
|
@ -488,14 +518,14 @@ doshortlink(const char *begin, const char *end, int newblock) {
|
|||
fputs("<a href=\"", stdout);
|
||||
if (ismail == 1) {
|
||||
/* mailto: */
|
||||
fputs("mailto:", stdout);
|
||||
fputs("mailto:",
|
||||
stdout);
|
||||
for (c = begin + 1; *c != '>'; c++)
|
||||
fprintf(stdout, "&#%u;", *c);
|
||||
fputs("\">", stdout);
|
||||
for (c = begin + 1; *c != '>'; c++)
|
||||
fprintf(stdout, "&#%u;", *c);
|
||||
}
|
||||
else {
|
||||
} else {
|
||||
hprint(begin + 1, p);
|
||||
fputs("\">", stdout);
|
||||
hprint(begin + 1, p);
|
||||
|
@ -507,14 +537,15 @@ doshortlink(const char *begin, const char *end, int newblock) {
|
|||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
dosurround(const char *begin, const char *end, int newblock) {
|
||||
int dosurround(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
unsigned int i, l;
|
||||
const char *p, *start, *stop;
|
||||
|
||||
for (i = 0; i < LENGTH(surround); i++) {
|
||||
l = strlen(surround[i].search);
|
||||
if(end - begin < 2*l || strncmp(begin, surround[i].search, l) != 0)
|
||||
if (end - begin < 2 * l ||
|
||||
strncmp(begin, surround[i].search, l) != 0)
|
||||
continue;
|
||||
start = begin + l;
|
||||
p = start - 1;
|
||||
|
@ -545,20 +576,24 @@ dosurround(const char *begin, const char *end, int newblock) {
|
|||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
dounderline(const char *begin, const char *end, int newblock) {
|
||||
int dounderline(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
unsigned int i, j, l;
|
||||
const char *p;
|
||||
|
||||
if (!newblock)
|
||||
return 0;
|
||||
p = begin;
|
||||
for(l = 0; p + l + 1 != end && p[l] != '\n'; l++);
|
||||
for (l = 0; p + l + 1 != end && p[l] != '\n'; l++)
|
||||
;
|
||||
p += l + 1;
|
||||
if (l == 0)
|
||||
return 0;
|
||||
for (i = 0; i < LENGTH(underline); i++) {
|
||||
for(j = 0; p + j != end && p[j] != '\n' && p[j] == underline[i].search[0]; j++);
|
||||
for (j = 0; p + j != end && p[j] != '\n' &&
|
||||
p[j] == underline[i].search[0];
|
||||
j++)
|
||||
;
|
||||
if (j >= l) {
|
||||
fputs(underline[i].before, stdout);
|
||||
if (underline[i].process)
|
||||
|
@ -572,8 +607,8 @@ dounderline(const char *begin, const char *end, int newblock) {
|
|||
return 0;
|
||||
}
|
||||
|
||||
void *
|
||||
ereallocz(void *p, size_t size) {
|
||||
void *ereallocz(void *p, size_t size)
|
||||
{
|
||||
void *res;
|
||||
if (p)
|
||||
res = realloc(p, size);
|
||||
|
@ -585,8 +620,8 @@ ereallocz(void *p, size_t size) {
|
|||
return res;
|
||||
}
|
||||
|
||||
void
|
||||
hprint(const char *begin, const char *end) {
|
||||
void hprint(const char *begin, const char *end)
|
||||
{
|
||||
const char *p;
|
||||
|
||||
for (p = begin; p != end; p++) {
|
||||
|
@ -603,8 +638,8 @@ hprint(const char *begin, const char *end) {
|
|||
}
|
||||
}
|
||||
|
||||
void
|
||||
process(const char *begin, const char *end, int newblock) {
|
||||
void process(const char *begin, const char *end, int newblock)
|
||||
{
|
||||
const char *p, *q;
|
||||
int affected;
|
||||
unsigned int i;
|
||||
|
@ -625,7 +660,8 @@ process(const char *begin, const char *end, int newblock) {
|
|||
fputc(*p, stdout);
|
||||
p++;
|
||||
}
|
||||
for(q = p; q != end && *q == '\n'; q++);
|
||||
for (q = p; q != end && *q == '\n'; q++)
|
||||
;
|
||||
if (q == end)
|
||||
return;
|
||||
else if (p[0] == '\n' && p + 1 != end && p[1] == '\n')
|
||||
|
@ -635,8 +671,8 @@ process(const char *begin, const char *end, int newblock) {
|
|||
}
|
||||
}
|
||||
|
||||
int
|
||||
main(int argc, char *argv[]) {
|
||||
int main(int argc, char *argv[])
|
||||
{
|
||||
char *buffer = NULL;
|
||||
int s, i;
|
||||
unsigned long len, bsize;
|
||||
|
@ -652,9 +688,9 @@ main(int argc, char *argv[]) {
|
|||
else if (!strcmp("--", argv[i])) {
|
||||
i++;
|
||||
break;
|
||||
}
|
||||
else
|
||||
eprint("Usage %s [-n] [file]\n -n escape html strictly\n", argv[0]);
|
||||
} else
|
||||
eprint("Usage %s [-n] [file]\n -n escape html strictly\n",
|
||||
argv[0]);
|
||||
}
|
||||
if (i < argc && !(source = fopen(argv[i], "r")))
|
||||
eprint("Cannot open file `%s`\n", argv[i]);
|
||||
|
|
Loading…
Add table
Reference in a new issue