📄 entities.c
字号:
* @doc: the document containing the string
* @input: A string to convert to XML.
*
* Do a global encoding of a string, replacing the predefined entities
* and non ASCII values with their entities and CharRef counterparts.
* Contrary to xmlEncodeEntities, this routine is reentrant, and result
* must be deallocated.
*
* Returns A newly allocated string with the substitution done.
*/
xmlChar *
xmlEncodeEntitiesReentrant(xmlDocPtr doc, const xmlChar *input) {
const xmlChar *cur = input;
xmlChar *buffer = NULL;
xmlChar *out = NULL;
int buffer_size = 0;
int html = 0;
if (input == NULL) return(NULL);
if (doc != NULL)
html = (doc->type == XML_HTML_DOCUMENT_NODE);
/*
* allocate an translation buffer.
*/
buffer_size = 1000;
buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
if (buffer == NULL) {
xmlEntitiesErrMemory("xmlEncodeEntitiesReentrant: malloc failed");
return(NULL);
}
out = buffer;
while (*cur != '\0') {
if (out - buffer > buffer_size - 100) {
int indx = out - buffer;
growBufferReentrant();
out = &buffer[indx];
}
/*
* By default one have to encode at least '<', '>', '"' and '&' !
*/
if (*cur == '<') {
*out++ = '&';
*out++ = 'l';
*out++ = 't';
*out++ = ';';
} else if (*cur == '>') {
*out++ = '&';
*out++ = 'g';
*out++ = 't';
*out++ = ';';
} else if (*cur == '&') {
*out++ = '&';
*out++ = 'a';
*out++ = 'm';
*out++ = 'p';
*out++ = ';';
} else if (((*cur >= 0x20) && (*cur < 0x80)) ||
(*cur == '\n') || (*cur == '\t') || ((html) && (*cur == '\r'))) {
/*
* default case, just copy !
*/
*out++ = *cur;
} else if (*cur >= 0x80) {
if (((doc != NULL) && (doc->encoding != NULL)) || (html)) {
/*
* Bj鴕n Reese <br@sseusa.com> provided the patch
xmlChar xc;
xc = (*cur & 0x3F) << 6;
if (cur[1] != 0) {
xc += *(++cur) & 0x3F;
*out++ = xc;
} else
*/
*out++ = *cur;
} else {
/*
* We assume we have UTF-8 input.
*/
char buf[11], *ptr;
int val = 0, l = 1;
if (*cur < 0xC0) {
xmlEntitiesErr(XML_CHECK_NOT_UTF8,
"xmlEncodeEntitiesReentrant : input not UTF-8");
if (doc != NULL)
doc->encoding = xmlStrdup(BAD_CAST "ISO-8859-1");
snprintf(buf, sizeof(buf), "&#%d;", *cur);
buf[sizeof(buf) - 1] = 0;
ptr = buf;
while (*ptr != 0) *out++ = *ptr++;
cur++;
continue;
} else if (*cur < 0xE0) {
val = (cur[0]) & 0x1F;
val <<= 6;
val |= (cur[1]) & 0x3F;
l = 2;
} else if (*cur < 0xF0) {
val = (cur[0]) & 0x0F;
val <<= 6;
val |= (cur[1]) & 0x3F;
val <<= 6;
val |= (cur[2]) & 0x3F;
l = 3;
} else if (*cur < 0xF8) {
val = (cur[0]) & 0x07;
val <<= 6;
val |= (cur[1]) & 0x3F;
val <<= 6;
val |= (cur[2]) & 0x3F;
val <<= 6;
val |= (cur[3]) & 0x3F;
l = 4;
}
if ((l == 1) || (!IS_CHAR(val))) {
xmlEntitiesErr(XML_ERR_INVALID_CHAR,
"xmlEncodeEntitiesReentrant : char out of range\n");
if (doc != NULL)
doc->encoding = xmlStrdup(BAD_CAST "ISO-8859-1");
snprintf(buf, sizeof(buf), "&#%d;", *cur);
buf[sizeof(buf) - 1] = 0;
ptr = buf;
while (*ptr != 0) *out++ = *ptr++;
cur++;
continue;
}
/*
* We could do multiple things here. Just save as a char ref
*/
if (html)
snprintf(buf, sizeof(buf), "&#%d;", val);
else
snprintf(buf, sizeof(buf), "&#x%X;", val);
buf[sizeof(buf) - 1] = 0;
ptr = buf;
while (*ptr != 0) *out++ = *ptr++;
cur += l;
continue;
}
} else if (IS_BYTE_CHAR(*cur)) {
char buf[11], *ptr;
snprintf(buf, sizeof(buf), "&#%d;", *cur);
buf[sizeof(buf) - 1] = 0;
ptr = buf;
while (*ptr != 0) *out++ = *ptr++;
}
cur++;
}
*out++ = 0;
return(buffer);
}
/**
* xmlEncodeSpecialChars:
* @doc: the document containing the string
* @input: A string to convert to XML.
*
* Do a global encoding of a string, replacing the predefined entities
* this routine is reentrant, and result must be deallocated.
*
* Returns A newly allocated string with the substitution done.
*/
xmlChar *
xmlEncodeSpecialChars(xmlDocPtr doc ATTRIBUTE_UNUSED, const xmlChar *input) {
const xmlChar *cur = input;
xmlChar *buffer = NULL;
xmlChar *out = NULL;
int buffer_size = 0;
if (input == NULL) return(NULL);
/*
* allocate an translation buffer.
*/
buffer_size = 1000;
buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
if (buffer == NULL) {
xmlEntitiesErrMemory("xmlEncodeSpecialChars: malloc failed");
return(NULL);
}
out = buffer;
while (*cur != '\0') {
if (out - buffer > buffer_size - 10) {
int indx = out - buffer;
growBufferReentrant();
out = &buffer[indx];
}
/*
* By default one have to encode at least '<', '>', '"' and '&' !
*/
if (*cur == '<') {
*out++ = '&';
*out++ = 'l';
*out++ = 't';
*out++ = ';';
} else if (*cur == '>') {
*out++ = '&';
*out++ = 'g';
*out++ = 't';
*out++ = ';';
} else if (*cur == '&') {
*out++ = '&';
*out++ = 'a';
*out++ = 'm';
*out++ = 'p';
*out++ = ';';
} else if (*cur == '"') {
*out++ = '&';
*out++ = 'q';
*out++ = 'u';
*out++ = 'o';
*out++ = 't';
*out++ = ';';
} else if (*cur == '\r') {
*out++ = '&';
*out++ = '#';
*out++ = '1';
*out++ = '3';
*out++ = ';';
} else {
/*
* Works because on UTF-8, all extended sequences cannot
* result in bytes in the ASCII range.
*/
*out++ = *cur;
}
cur++;
}
*out++ = 0;
return(buffer);
}
/**
* xmlCreateEntitiesTable:
*
* create and initialize an empty entities hash table.
* This really doesn't make sense and should be deprecated
*
* Returns the xmlEntitiesTablePtr just created or NULL in case of error.
*/
xmlEntitiesTablePtr
xmlCreateEntitiesTable(void) {
return((xmlEntitiesTablePtr) xmlHashCreate(0));
}
/**
* xmlFreeEntityWrapper:
* @entity: An entity
* @name: its name
*
* Deallocate the memory used by an entities in the hash table.
*/
static void
xmlFreeEntityWrapper(xmlEntityPtr entity,
const xmlChar *name ATTRIBUTE_UNUSED) {
if (entity != NULL)
xmlFreeEntity(entity);
}
/**
* xmlFreeEntitiesTable:
* @table: An entity table
*
* Deallocate the memory used by an entities hash table.
*/
void
xmlFreeEntitiesTable(xmlEntitiesTablePtr table) {
xmlHashFree(table, (xmlHashDeallocator) xmlFreeEntityWrapper);
}
#ifdef LIBXML_TREE_ENABLED
/**
* xmlCopyEntity:
* @ent: An entity
*
* Build a copy of an entity
*
* Returns the new xmlEntitiesPtr or NULL in case of error.
*/
static xmlEntityPtr
xmlCopyEntity(xmlEntityPtr ent) {
xmlEntityPtr cur;
cur = (xmlEntityPtr) xmlMalloc(sizeof(xmlEntity));
if (cur == NULL) {
xmlEntitiesErrMemory("xmlCopyEntity:: malloc failed");
return(NULL);
}
memset(cur, 0, sizeof(xmlEntity));
cur->type = XML_ENTITY_DECL;
cur->etype = ent->etype;
if (ent->name != NULL)
cur->name = xmlStrdup(ent->name);
if (ent->ExternalID != NULL)
cur->ExternalID = xmlStrdup(ent->ExternalID);
if (ent->SystemID != NULL)
cur->SystemID = xmlStrdup(ent->SystemID);
if (ent->content != NULL)
cur->content = xmlStrdup(ent->content);
if (ent->orig != NULL)
cur->orig = xmlStrdup(ent->orig);
if (ent->URI != NULL)
cur->URI = xmlStrdup(ent->URI);
return(cur);
}
/**
* xmlCopyEntitiesTable:
* @table: An entity table
*
* Build a copy of an entity table.
*
* Returns the new xmlEntitiesTablePtr or NULL in case of error.
*/
xmlEntitiesTablePtr
xmlCopyEntitiesTable(xmlEntitiesTablePtr table) {
return(xmlHashCopy(table, (xmlHashCopier) xmlCopyEntity));
}
#endif /* LIBXML_TREE_ENABLED */
#ifdef LIBXML_OUTPUT_ENABLED
/**
* xmlDumpEntityContent:
* @buf: An XML buffer.
* @content: The entity content.
*
* This will dump the quoted string value, taking care of the special
* treatment required by %
*/
static void
xmlDumpEntityContent(xmlBufferPtr buf, const xmlChar *content) {
if (buf->alloc == XML_BUFFER_ALLOC_IMMUTABLE) return;
if (xmlStrchr(content, '%')) {
const xmlChar * base, *cur;
xmlBufferCCat(buf, "\"");
base = cur = content;
while (*cur != 0) {
if (*cur == '"') {
if (base != cur)
xmlBufferAdd(buf, base, cur - base);
xmlBufferAdd(buf, BAD_CAST """, 6);
cur++;
base = cur;
} else if (*cur == '%') {
if (base != cur)
xmlBufferAdd(buf, base, cur - base);
xmlBufferAdd(buf, BAD_CAST "%", 6);
cur++;
base = cur;
} else {
cur++;
}
}
if (base != cur)
xmlBufferAdd(buf, base, cur - base);
xmlBufferCCat(buf, "\"");
} else {
xmlBufferWriteQuotedString(buf, content);
}
}
/**
* xmlDumpEntityDecl:
* @buf: An XML buffer.
* @ent: An entity table
*
* This will dump the content of the entity table as an XML DTD definition
*/
void
xmlDumpEntityDecl(xmlBufferPtr buf, xmlEntityPtr ent) {
if ((buf == NULL) || (ent == NULL)) return;
switch (ent->etype) {
case XML_INTERNAL_GENERAL_ENTITY:
xmlBufferWriteChar(buf, "<!ENTITY ");
xmlBufferWriteCHAR(buf, ent->name);
xmlBufferWriteChar(buf, " ");
if (ent->orig != NULL)
xmlBufferWriteQuotedString(buf, ent->orig);
else
xmlDumpEntityContent(buf, ent->content);
xmlBufferWriteChar(buf, ">\n");
break;
case XML_EXTERNAL_GENERAL_PARSED_ENTITY:
xmlBufferWriteChar(buf, "<!ENTITY ");
xmlBufferWriteCHAR(buf, ent->name);
if (ent->ExternalID != NULL) {
xmlBufferWriteChar(buf, " PUBLIC ");
xmlBufferWriteQuotedString(buf, ent->ExternalID);
xmlBufferWriteChar(buf, " ");
xmlBufferWriteQuotedString(buf, ent->SystemID);
} else {
xmlBufferWriteChar(buf, " SYSTEM ");
xmlBufferWriteQuotedString(buf, ent->SystemID);
}
xmlBufferWriteChar(buf, ">\n");
break;
case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY:
xmlBufferWriteChar(buf, "<!ENTITY ");
xmlBufferWriteCHAR(buf, ent->name);
if (ent->ExternalID != NULL) {
xmlBufferWriteChar(buf, " PUBLIC ");
xmlBufferWriteQuotedString(buf, ent->ExternalID);
xmlBufferWriteChar(buf, " ");
xmlBufferWriteQuotedString(buf, ent->SystemID);
} else {
xmlBufferWriteChar(buf, " SYSTEM ");
xmlBufferWriteQuotedString(buf, ent->SystemID);
}
if (ent->content != NULL) { /* Should be true ! */
xmlBufferWriteChar(buf, " NDATA ");
if (ent->orig != NULL)
xmlBufferWriteCHAR(buf, ent->orig);
else
xmlBufferWriteCHAR(buf, ent->content);
}
xmlBufferWriteChar(buf, ">\n");
break;
case XML_INTERNAL_PARAMETER_ENTITY:
xmlBufferWriteChar(buf, "<!ENTITY % ");
xmlBufferWriteCHAR(buf, ent->name);
xmlBufferWriteChar(buf, " ");
if (ent->orig == NULL)
xmlDumpEntityContent(buf, ent->content);
else
xmlBufferWriteQuotedString(buf, ent->orig);
xmlBufferWriteChar(buf, ">\n");
break;
case XML_EXTERNAL_PARAMETER_ENTITY:
xmlBufferWriteChar(buf, "<!ENTITY % ");
xmlBufferWriteCHAR(buf, ent->name);
if (ent->ExternalID != NULL) {
xmlBufferWriteChar(buf, " PUBLIC ");
xmlBufferWriteQuotedString(buf, ent->ExternalID);
xmlBufferWriteChar(buf, " ");
xmlBufferWriteQuotedString(buf, ent->SystemID);
} else {
xmlBufferWriteChar(buf, " SYSTEM ");
xmlBufferWriteQuotedString(buf, ent->SystemID);
}
xmlBufferWriteChar(buf, ">\n");
break;
default:
xmlEntitiesErr(XML_DTD_UNKNOWN_ENTITY,
"xmlDumpEntitiesDecl: internal: unknown type entity type");
}
}
/**
* xmlDumpEntityDeclScan:
* @ent: An entity table
* @buf: An XML buffer.
*
* When using the hash table scan function, arguments need to be reversed
*/
static void
xmlDumpEntityDeclScan(xmlEntityPtr ent, xmlBufferPtr buf) {
xmlDumpEntityDecl(buf, ent);
}
/**
* xmlDumpEntitiesTable:
* @buf: An XML buffer.
* @table: An entity table
*
* This will dump the content of the entity table as an XML DTD definition
*/
void
xmlDumpEntitiesTable(xmlBufferPtr buf, xmlEntitiesTablePtr table) {
xmlHashScan(table, (xmlHashScanner)xmlDumpEntityDeclScan, buf);
}
#endif /* LIBXML_OUTPUT_ENABLED */
#define bottom_entities
#include "elfgcchack.h"
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -