initial commit - xml2tsv - a simple xml-to-tsv converter, based on xmlparser
DIR Log
DIR Files
DIR Refs
DIR Tags
DIR README
DIR LICENSE
---
DIR commit d10d115bb1de07e38a31f2e5946150f1f86e2d3e
HTML Author: KatolaZ <katolaz@freaknet.org>
Date: Fri, 3 Jan 2020 12:25:34 +0000
initial commit
Diffstat:
A LICENSE | 15 +++++++++++++++
A xml.c | 454 +++++++++++++++++++++++++++++++
A xml.h | 47 +++++++++++++++++++++++++++++++
A xml2tsv.c | 228 +++++++++++++++++++++++++++++++
4 files changed, 744 insertions(+), 0 deletions(-)
---
DIR diff --git a/LICENSE b/LICENSE
@@ -0,0 +1,15 @@
+ISC License
+
+Copyright (c) 2020 Vincenzo "KatolaZ" Nicosia <katolaz@freaknet.org>
+
+Permission to use, copy, modify, and/or distribute this software for any
+purpose with or without fee is hereby granted, provided that the above
+copyright notice and this permission notice appear in all copies.
+
+THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
DIR diff --git a/xml.c b/xml.c
@@ -0,0 +1,454 @@
+#include <sys/types.h>
+
+#include <ctype.h>
+#include <errno.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "xml.h"
+
+static void
+xml_parseattrs(XMLParser *x)
+{
+ size_t namelen = 0, valuelen;
+ int c, endsep, endname = 0, valuestart = 0;
+
+ while ((c = GETNEXT()) != EOF) {
+ if (isspace(c)) {
+ if (namelen)
+ endname = 1;
+ continue;
+ } else if (c == '?')
+ ; /* ignore */
+ else if (c == '=') {
+ x->name[namelen] = '\0';
+ valuestart = 1;
+ endname = 1;
+ } else if (namelen && ((endname && !valuestart && isalpha(c)) || (c == '>' || c == '/'))) {
+ /* attribute without value */
+ x->name[namelen] = '\0';
+ if (x->xmlattrstart)
+ x->xmlattrstart(x, x->tag, x->taglen, x->name, namelen);
+ if (x->xmlattr)
+ x->xmlattr(x, x->tag, x->taglen, x->name, namelen, "", 0);
+ if (x->xmlattrend)
+ x->xmlattrend(x, x->tag, x->taglen, x->name, namelen);
+ endname = 0;
+ x->name[0] = c;
+ namelen = 1;
+ } else if (namelen && valuestart) {
+ /* attribute with value */
+ if (x->xmlattrstart)
+ x->xmlattrstart(x, x->tag, x->taglen, x->name, namelen);
+
+ valuelen = 0;
+ if (c == '\'' || c == '"') {
+ endsep = c;
+ } else {
+ endsep = ' '; /* isspace() */
+ goto startvalue;
+ }
+
+ while ((c = GETNEXT()) != EOF) {
+startvalue:
+ if (c == '&') { /* entities */
+ x->data[valuelen] = '\0';
+ /* call data function with data before entity if there is data */
+ if (valuelen && x->xmlattr)
+ x->xmlattr(x, x->tag, x->taglen, x->name, namelen, x->data, valuelen);
+ x->data[0] = c;
+ valuelen = 1;
+ while ((c = GETNEXT()) != EOF) {
+ if (c == endsep || (endsep == ' ' && (c == '>' || isspace(c))))
+ break;
+ if (valuelen < sizeof(x->data) - 1)
+ x->data[valuelen++] = c;
+ else {
+ /* entity too long for buffer, handle as normal data */
+ x->data[valuelen] = '\0';
+ if (x->xmlattr)
+ x->xmlattr(x, x->tag, x->taglen, x->name, namelen, x->data, valuelen);
+ x->data[0] = c;
+ valuelen = 1;
+ break;
+ }
+ if (c == ';') {
+ x->data[valuelen] = '\0';
+ if (x->xmlattrentity)
+ x->xmlattrentity(x, x->tag, x->taglen, x->name, namelen, x->data, valuelen);
+ valuelen = 0;
+ break;
+ }
+ }
+ } else if (c != endsep && !(endsep == ' ' && (c == '>' || isspace(c)))) {
+ if (valuelen < sizeof(x->data) - 1) {
+ x->data[valuelen++] = c;
+ } else {
+ x->data[valuelen] = '\0';
+ if (x->xmlattr)
+ x->xmlattr(x, x->tag, x->taglen, x->name, namelen, x->data, valuelen);
+ x->data[0] = c;
+ valuelen = 1;
+ }
+ }
+ if (c == endsep || (endsep == ' ' && (c == '>' || isspace(c)))) {
+ x->data[valuelen] = '\0';
+ if (x->xmlattr)
+ x->xmlattr(x, x->tag, x->taglen, x->name, namelen, x->data, valuelen);
+ if (x->xmlattrend)
+ x->xmlattrend(x, x->tag, x->taglen, x->name, namelen);
+ break;
+ }
+ }
+ namelen = endname = valuestart = 0;
+ } else if (namelen < sizeof(x->name) - 1) {
+ x->name[namelen++] = c;
+ }
+ if (c == '>') {
+ break;
+ } else if (c == '/') {
+ x->isshorttag = 1;
+ x->name[0] = '\0';
+ namelen = 0;
+ }
+ }
+}
+
+static void
+xml_parsecomment(XMLParser *x)
+{
+ size_t datalen = 0, i = 0;
+ int c;
+
+ if (x->xmlcommentstart)
+ x->xmlcommentstart(x);
+ while ((c = GETNEXT()) != EOF) {
+ if (c == '-' || c == '>') {
+ if (x->xmlcomment && datalen) {
+ x->data[datalen] = '\0';
+ x->xmlcomment(x, x->data, datalen);
+ datalen = 0;
+ }
+ }
+
+ if (c == '-') {
+ if (++i > 2) {
+ if (x->xmlcomment)
+ for (; i > 2; i--)
+ x->xmlcomment(x, "-", 1);
+ i = 2;
+ }
+ continue;
+ } else if (c == '>' && i == 2) {
+ if (x->xmlcommentend)
+ x->xmlcommentend(x);
+ return;
+ } else if (i) {
+ if (x->xmlcomment) {
+ for (; i > 0; i--)
+ x->xmlcomment(x, "-", 1);
+ }
+ i = 0;
+ }
+
+ if (datalen < sizeof(x->data) - 1) {
+ x->data[datalen++] = c;
+ } else {
+ x->data[datalen] = '\0';
+ if (x->xmlcomment)
+ x->xmlcomment(x, x->data, datalen);
+ x->data[0] = c;
+ datalen = 1;
+ }
+ }
+}
+
+static void
+xml_parsecdata(XMLParser *x)
+{
+ size_t datalen = 0, i = 0;
+ int c;
+
+ if (x->xmlcdatastart)
+ x->xmlcdatastart(x);
+ while ((c = GETNEXT()) != EOF) {
+ if (c == ']' || c == '>') {
+ if (x->xmlcdata && datalen) {
+ x->data[datalen] = '\0';
+ x->xmlcdata(x, x->data, datalen);
+ datalen = 0;
+ }
+ }
+
+ if (c == ']') {
+ if (++i > 2) {
+ if (x->xmlcdata)
+ for (; i > 2; i--)
+ x->xmlcdata(x, "]", 1);
+ i = 2;
+ }
+ continue;
+ } else if (c == '>' && i == 2) {
+ if (x->xmlcdataend)
+ x->xmlcdataend(x);
+ return;
+ } else if (i) {
+ if (x->xmlcdata)
+ for (; i > 0; i--)
+ x->xmlcdata(x, "]", 1);
+ i = 0;
+ }
+
+ if (datalen < sizeof(x->data) - 1) {
+ x->data[datalen++] = c;
+ } else {
+ x->data[datalen] = '\0';
+ if (x->xmlcdata)
+ x->xmlcdata(x, x->data, datalen);
+ x->data[0] = c;
+ datalen = 1;
+ }
+ }
+}
+
+static int
+codepointtoutf8(long r, char *s)
+{
+ if (r == 0) {
+ return 0; /* NUL byte */
+ } else if (r <= 0x7F) {
+ /* 1 byte: 0aaaaaaa */
+ s[0] = r;
+ return 1;
+ } else if (r <= 0x07FF) {
+ /* 2 bytes: 00000aaa aabbbbbb */
+ s[0] = 0xC0 | ((r & 0x0007C0) >> 6); /* 110aaaaa */
+ s[1] = 0x80 | (r & 0x00003F); /* 10bbbbbb */
+ return 2;
+ } else if (r <= 0xFFFF) {
+ /* 3 bytes: aaaabbbb bbcccccc */
+ s[0] = 0xE0 | ((r & 0x00F000) >> 12); /* 1110aaaa */
+ s[1] = 0x80 | ((r & 0x000FC0) >> 6); /* 10bbbbbb */
+ s[2] = 0x80 | (r & 0x00003F); /* 10cccccc */
+ return 3;
+ } else {
+ /* 4 bytes: 000aaabb bbbbcccc ccdddddd */
+ s[0] = 0xF0 | ((r & 0x1C0000) >> 18); /* 11110aaa */
+ s[1] = 0x80 | ((r & 0x03F000) >> 12); /* 10bbbbbb */
+ s[2] = 0x80 | ((r & 0x000FC0) >> 6); /* 10cccccc */
+ s[3] = 0x80 | (r & 0x00003F); /* 10dddddd */
+ return 4;
+ }
+}
+
+static int
+namedentitytostr(const char *e, char *buf, size_t bufsiz)
+{
+ static const struct {
+ const char *entity;
+ int c;
+ } entities[] = {
+ { "amp;", '&' },
+ { "lt;", '<' },
+ { "gt;", '>' },
+ { "apos;", '\'' },
+ { "quot;", '"' },
+ };
+ size_t i;
+
+ /* buffer is too small */
+ if (bufsiz < 2)
+ return -1;
+
+ for (i = 0; i < sizeof(entities) / sizeof(*entities); i++) {
+ if (!strcmp(e, entities[i].entity)) {
+ buf[0] = entities[i].c;
+ buf[1] = '\0';
+ return 1;
+ }
+ }
+ return 0;
+}
+
+static int
+numericentitytostr(const char *e, char *buf, size_t bufsiz)
+{
+ long l;
+ int len;
+ char *end;
+
+ /* buffer is too small */
+ if (bufsiz < 5)
+ return -1;
+
+ errno = 0;
+ /* hex (16) or decimal (10) */
+ if (*e == 'x')
+ l = strtoul(e + 1, &end, 16);
+ else
+ l = strtoul(e, &end, 10);
+ /* invalid value or not a well-formed entity or too high codepoint */
+ if (errno || *end != ';' || l > 0x10FFFF)
+ return 0;
+ len = codepointtoutf8(l, buf);
+ buf[len] = '\0';
+
+ return len;
+}
+
+/* convert named- or numeric entity string to buffer string
+ * returns byte-length of string. */
+int
+xml_entitytostr(const char *e, char *buf, size_t bufsiz)
+{
+ /* doesn't start with & */
+ if (e[0] != '&')
+ return 0;
+ /* numeric entity */
+ if (e[1] == '#')
+ return numericentitytostr(e + 2, buf, bufsiz);
+ else /* named entity */
+ return namedentitytostr(e + 1, buf, bufsiz);
+}
+
+void
+xml_parse(XMLParser *x)
+{
+ size_t datalen, tagdatalen;
+ int c, isend;
+
+ while ((c = GETNEXT()) != EOF && c != '<')
+ ; /* skip until < */
+
+ while (c != EOF) {
+ if (c == '<') { /* parse tag */
+ if ((c = GETNEXT()) == EOF)
+ return;
+
+ if (c == '!') { /* cdata and comments */
+ for (tagdatalen = 0; (c = GETNEXT()) != EOF;) {
+ /* NOTE: sizeof(x->data) must be atleast sizeof("[CDATA[") */
+ if (tagdatalen <= sizeof("[CDATA[") - 1)
+ x->data[tagdatalen++] = c;
+ if (c == '>')
+ break;
+ else if (c == '-' && tagdatalen == sizeof("--") - 1 &&
+ (x->data[0] == '-')) {
+ xml_parsecomment(x);
+ break;
+ } else if (c == '[') {
+ if (tagdatalen == sizeof("[CDATA[") - 1 &&
+ !strncmp(x->data, "[CDATA[", tagdatalen)) {
+ xml_parsecdata(x);
+ break;
+ }
+ }
+ }
+ } else {
+ /* normal tag (open, short open, close), processing instruction. */
+ x->tag[0] = c;
+ x->taglen = 1;
+ x->isshorttag = isend = 0;
+
+ /* treat processing instruction as shorttag, don't strip "?" prefix. */
+ if (c == '?') {
+ x->isshorttag = 1;
+ } else if (c == '/') {
+ if ((c = GETNEXT()) == EOF)
+ return;
+ x->tag[0] = c;
+ isend = 1;
+ }
+
+ while ((c = GETNEXT()) != EOF) {
+ if (c == '/')
+ x->isshorttag = 1; /* short tag */
+ else if (c == '>' || isspace(c)) {
+ x->tag[x->taglen] = '\0';
+ if (isend) { /* end tag, starts with </ */
+ if (x->xmltagend)
+ x->xmltagend(x, x->tag, x->taglen, x->isshorttag);
+ x->tag[0] = '\0';
+ x->taglen = 0;
+ } else {
+ /* start tag */
+ if (x->xmltagstart)
+ x->xmltagstart(x, x->tag, x->taglen);
+ if (isspace(c))
+ xml_parseattrs(x);
+ if (x->xmltagstartparsed)
+ x->xmltagstartparsed(x, x->tag, x->taglen, x->isshorttag);
+ }
+ /* call tagend for shortform or processing instruction */
+ if (x->isshorttag) {
+ if (x->xmltagend)
+ x->xmltagend(x, x->tag, x->taglen, x->isshorttag);
+ x->tag[0] = '\0';
+ x->taglen = 0;
+ }
+ break;
+ } else if (x->taglen < sizeof(x->tag) - 1)
+ x->tag[x->taglen++] = c; /* NOTE: tag name truncation */
+ }
+ }
+ } else {
+ /* parse tag data */
+ datalen = 0;
+ if (x->xmldatastart)
+ x->xmldatastart(x);
+ while ((c = GETNEXT()) != EOF) {
+ if (c == '&') {
+ if (datalen) {
+ x->data[datalen] = '\0';
+ if (x->xmldata)
+ x->xmldata(x, x->data, datalen);
+ }
+ x->data[0] = c;
+ datalen = 1;
+ while ((c = GETNEXT()) != EOF) {
+ if (c == '<')
+ break;
+ if (datalen < sizeof(x->data) - 1)
+ x->data[datalen++] = c;
+ else {
+ /* entity too long for buffer, handle as normal data */
+ x->data[datalen] = '\0';
+ if (x->xmldata)
+ x->xmldata(x, x->data, datalen);
+ x->data[0] = c;
+ datalen = 1;
+ break;
+ }
+ if (c == ';') {
+ x->data[datalen] = '\0';
+ if (x->xmldataentity)
+ x->xmldataentity(x, x->data, datalen);
+ datalen = 0;
+ break;
+ }
+ }
+ } else if (c != '<') {
+ if (datalen < sizeof(x->data) - 1) {
+ x->data[datalen++] = c;
+ } else {
+ x->data[datalen] = '\0';
+ if (x->xmldata)
+ x->xmldata(x, x->data, datalen);
+ x->data[0] = c;
+ datalen = 1;
+ }
+ }
+ if (c == '<') {
+ x->data[datalen] = '\0';
+ if (x->xmldata && datalen)
+ x->xmldata(x, x->data, datalen);
+ if (x->xmldataend)
+ x->xmldataend(x);
+ break;
+ }
+ }
+ }
+ }
+}
DIR diff --git a/xml.h b/xml.h
@@ -0,0 +1,47 @@
+#ifndef _XML_H
+#define _XML_H
+
+typedef struct xmlparser {
+ /* handlers */
+ void (*xmlattr)(struct xmlparser *, const char *, size_t,
+ const char *, size_t, const char *, size_t);
+ void (*xmlattrend)(struct xmlparser *, const char *, size_t,
+ const char *, size_t);
+ void (*xmlattrstart)(struct xmlparser *, const char *, size_t,
+ const char *, size_t);
+ void (*xmlattrentity)(struct xmlparser *, const char *, size_t,
+ const char *, size_t, const char *, size_t);
+ void (*xmlcdatastart)(struct xmlparser *);
+ void (*xmlcdata)(struct xmlparser *, const char *, size_t);
+ void (*xmlcdataend)(struct xmlparser *);
+ void (*xmlcommentstart)(struct xmlparser *);
+ void (*xmlcomment)(struct xmlparser *, const char *, size_t);
+ void (*xmlcommentend)(struct xmlparser *);
+ void (*xmldata)(struct xmlparser *, const char *, size_t);
+ void (*xmldataend)(struct xmlparser *);
+ void (*xmldataentity)(struct xmlparser *, const char *, size_t);
+ void (*xmldatastart)(struct xmlparser *);
+ void (*xmltagend)(struct xmlparser *, const char *, size_t, int);
+ void (*xmltagstart)(struct xmlparser *, const char *, size_t);
+ void (*xmltagstartparsed)(struct xmlparser *, const char *,
+ size_t, int);
+
+#ifndef GETNEXT
+ #define GETNEXT (x)->getnext
+ int (*getnext)(void);
+#endif
+
+ /* current tag */
+ char tag[1024];
+ size_t taglen;
+ /* current tag is in short form ? <tag /> */
+ int isshorttag;
+ /* current attribute name */
+ char name[1024];
+ /* data buffer used for tag data, cdata and attribute data */
+ char data[BUFSIZ];
+} XMLParser;
+
+int xml_entitytostr(const char *, char *, size_t);
+void xml_parse(XMLParser *);
+#endif
DIR diff --git a/xml2tsv.c b/xml2tsv.c
@@ -0,0 +1,228 @@
+/*
+* (c) 2020 Vincenzo "KatolaZ" Nicosia <katolaz@freaknet.org>
+*
+* A simple xml-to-rsv converter, based on xmlparser by Hiltjo Posthuma
+* http://codemadness.org/git/xmlparser/
+*
+* You can use, distribute, modify, and/or redistribute this program under
+* the terms of the ISC LICENSE. See LICENSE for details.
+*
+*/
+
+
+#include <sys/types.h>
+
+#include <stdio.h>
+#include <string.h>
+
+#include "xml.h"
+
+#define STR_MAX 128
+#define DEPTH_MAX 50
+
+
+/* tag stack */
+
+typedef struct {
+ int top;
+ char st[DEPTH_MAX][STR_MAX];
+} tstack_t;
+
+int stack_push(tstack_t *t, const char *c){
+ if (t->top < DEPTH_MAX){
+ t->top ++;
+ strncpy(t->st[t->top], c, STR_MAX);
+ return 0;
+ }
+ return -1;
+}
+
+char* stack_pop(tstack_t *t){
+ if (t->top >= 0)
+ return t->st[t->top--];
+ return NULL;
+}
+
+char* stack_peek(tstack_t *t){
+ if (t->top >= 0)
+ return t->st[t->top];
+ return NULL;
+}
+
+int stack_empty(tstack_t *t){
+ return (t->top < 0);
+}
+
+void stack_init(tstack_t *t){
+ t->top = -1;
+}
+
+
+/* utility functions */
+
+void print_no_cr(FILE *f, const char *c){
+ char *tmp = c;
+ while (c != NULL){
+ tmp = strchr(c, '\n');
+ if (tmp != NULL)
+ *tmp = '\0';
+ fprintf(f, "%s", c);
+ if (tmp != NULL)
+ c = tmp + 1;
+ else
+ c = NULL;
+ }
+}
+
+void print_cur_str(FILE *f, tstack_t *t){
+ int i;
+ for (i=0; i<=t->top; i++){
+ fprintf(f, "/%s", t->st[i]);
+ }
+}
+
+/* global variables */
+
+tstack_t st;
+
+
+/* xml callbacks */
+
+void
+xmlattr(XMLParser *x, const char *t, size_t tl, const char *a, size_t al,
+ const char *v, size_t vl)
+{
+ printf("\t%s=%s", a, v);
+}
+
+void
+xmlattrentity(XMLParser *x, const char *t, size_t tl, const char *a, size_t al,
+ const char *v, size_t vl)
+{
+ printf("attrentity: %s\n", a);
+}
+
+void
+xmlattrend(XMLParser *x, const char *t, size_t tl, const char *a, size_t al)
+{
+}
+
+void
+xmlattrstart(XMLParser *x, const char *t, size_t tl, const char *a, size_t al)
+{
+}
+
+void
+xmlcdatastart(XMLParser *x)
+{
+}
+
+void
+xmlcdata(XMLParser *x, const char *d, size_t dl)
+{
+ printf("\t%s", d);
+}
+
+void
+xmlcdataend(XMLParser *x)
+{
+}
+
+void
+xmlcommentstart(XMLParser *x)
+{
+}
+
+void
+xmlcomment(XMLParser *x, const char *c, size_t cl)
+{
+}
+
+void
+xmlcommentend(XMLParser *x)
+{
+}
+
+void
+xmldata(XMLParser *x, const char *d, size_t dl)
+{
+ printf("\t");
+ print_no_cr(stdout, d);
+}
+
+void
+xmldataend(XMLParser *x)
+{
+}
+
+void
+xmldataentity(XMLParser *x, const char *d, size_t dl)
+{
+}
+
+void
+xmldatastart(XMLParser *x)
+{
+}
+
+void
+xmltagend(XMLParser *x, const char *t, size_t tl, int isshort)
+{
+ char *tag;
+ if (stack_empty(&st)){
+ fprintf(stderr, "Error: tag-end '%s' before any open tag", t);
+ }
+ tag = stack_pop(&st);
+ if (strcmp(t, tag)){
+ fprintf(stderr, "Error: tag-end '%s' closes tag '%s'", t, tag);
+ }
+ /* printf("\n"); */
+}
+
+void
+xmltagstart(XMLParser *x, const char *t, size_t tl)
+{
+ if (stack_push(&st, t)){
+ fprintf(stderr, "Error: stack full. Ignoring tag '%s' (parent tag: '%s')\n", t, stack_peek(&st));
+ return;
+ }
+ printf("\n");
+ print_cur_str(stdout, &st);
+}
+
+void
+xmltagstartparsed(XMLParser *x, const char *t, size_t tl, int isshort)
+{
+ /* printf("inside tagstartparsed\n"); */
+}
+
+int
+main(void)
+{
+ stack_init(&st);
+ XMLParser x = { 0 };
+
+ x.xmlattr = xmlattr;
+ x.xmlattrend = xmlattrend;
+ x.xmlattrstart = xmlattrstart;
+ x.xmlattrentity = xmlattrentity;
+ x.xmlcdatastart = xmlcdatastart;
+ x.xmlcdata = xmlcdata;
+ x.xmlcdataend = xmlcdataend;
+ x.xmlcommentstart = xmlcommentstart;
+ x.xmlcomment = xmlcomment;
+ x.xmlcommentend = xmlcommentend;
+ x.xmldata = xmldata;
+ x.xmldataend = xmldataend;
+ x.xmldataentity = xmldataentity;
+ x.xmldatastart = xmldatastart;
+ x.xmltagend = xmltagend;
+ x.xmltagstart = xmltagstart;
+ x.xmltagstartparsed = xmltagstartparsed;
+
+ x.getnext = getchar;
+
+ xml_parse(&x);
+ printf("\n");
+ return 0;
+}