/*
* Summary: the core parser module
* Description: Interfaces, constants and types related to the XML parser
*
* Copy: See Copyright for the status of this software.
*
* Author: Daniel Veillard
*/
#ifndef __XML_PARSER_H__
#define __XML_PARSER_H__
#include <stdarg.h>
#include <libxml/xmlversion.h>
#include <libxml/tree.h>
#include <libxml/dict.h>
#include <libxml/hash.h>
#include <libxml/valid.h>
#include <libxml/entities.h>
#include <libxml/xmlerror.h>
#include <libxml/xmlstring.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* XML_DEFAULT_VERSION:
*
* The default version of XML used: 1.0
*/
#define XML_DEFAULT_VERSION "1.0"
/**
* xmlParserInput:
*
* An xmlParserInput is an input flow for the XML processor.
* Each entity parsed is associated an xmlParserInput (except the
* few predefined ones). This is the case both for internal entities
* - in which case the flow is already completely in memory - or
* external entities - in which case we use the buf structure for
* progressive reading and I18N conversions to the internal UTF-8 format.
*/
/**
* xmlParserInputDeallocate:
* @str: the string to deallocate
*
* Callback for freeing some parser input allocations.
*/
typedef void (* xmlParserInputDeallocate)(xmlChar *str);
struct _xmlParserInput {
/* Input buffer */
xmlParserInputBufferPtr buf; /* UTF-8 encoded buffer */
const char *filename; /* The file analyzed, if any */
const char *directory; /* the directory/base of the file */
const xmlChar *base; /* Base of the array to parse */
const xmlChar *cur; /* Current char being parsed */
const xmlChar *end; /* end of the array to parse */
int length; /* length if known */
int line; /* Current line */
int col; /* Current column */
/*
* NOTE: consumed is only tested for equality in the parser code,
* so even if there is an overflow this should not give troubles
* for parsing very large instances.
*/
unsigned long consumed; /* How many xmlChars already consumed */
xmlParserInputDeallocate free; /* function to deallocate the base */
const xmlChar *encoding; /* the encoding string for entity */
const xmlChar *version; /* the version string for entity */
int standalone; /* Was that entity marked standalone */
int id; /* an unique identifier for the entity */
};
/**
* xmlParserNodeInfo:
*
* The parser can be asked to collect Node informations, i.e. at what
* place in the file they were detected.
* NOTE: This is off by default and not very well tested.
*/
typedef struct _xmlParserNodeInfo xmlParserNodeInfo;
typedef xmlParserNodeInfo *xmlParserNodeInfoPtr;
struct _xmlParserNodeInfo {
const struct _xmlNode* node;
/* Position & line # that text that created the node begins & ends on */
unsigned long begin_pos;
unsigned long begin_line;
unsigned long end_pos;
unsigned long end_line;
};
typedef struct _xmlParserNodeInfoSeq xmlParserNodeInfoSeq;
typedef xmlParserNodeInfoSeq *xmlParserNodeInfoSeqPtr;
struct _xmlParserNodeInfoSeq {
unsigned long maximum;
unsigned long length;
xmlParserNodeInfo* buffer;
};
/**
* xmlParserInputState:
*
* The parser is now working also as a state based parser.
* The recursive one use the state info for entities processing.
*/
typedef enum {
XML_PARSER_EOF = -1, /* nothing is to be parsed */
XML_PARSER_START = 0, /* nothing has been parsed */
XML_PARSER_MISC, /* Misc* before int subset */
XML_PARSER_PI, /* Within a processing instruction */
XML_PARSER_DTD, /* within some DTD content */
XML_PARSER_PROLOG, /* Misc* after internal subset */
XML_PARSER_COMMENT, /* within a comment */
XML_PARSER_START_TAG, /* within a start tag */
XML_PARSER_CONTENT, /* within the content */
XML_PARSER_CDATA_SECTION, /* within a CDATA section */
XML_PARSER_END_TAG, /* within a closing tag */
XML_PARSER_ENTITY_DECL, /* within an entity declaration */
XML_PARSER_ENTITY_VALUE, /* within an entity value in a decl */
XML_PARSER_ATTRIBUTE_VALUE, /* within an attribute value */
XML_PARSER_SYSTEM_LITERAL, /* within a SYSTEM value */
XML_PARSER_EPILOG, /* the Misc* after the last end tag */
XML_PARSER_IGNORE, /* within an IGNORED section */
XML_PARSER_PUBLIC_LITERAL /* within a PUBLIC value */
} xmlParserInputState;
/**
* XML_DETECT_IDS:
*
* Bit in the loadsubset context field to tell to do ID/REFs lookups.
* Use it to initialize xmlLoadExtDtdDefaultValue.
*/
#define XML_DETECT_IDS 2
/**
* XML_COMPLETE_ATTRS:
*
* Bit in the loadsubset context field to tell to do complete the
* elements attributes lists with the ones defaulted from the DTDs.
* Use it to initialize xmlLoadExtDtdDefaultValue.
*/
#define XML_COMPLETE_ATTRS 4
/**
* XML_SKIP_IDS:
*
* Bit in the loadsubset context field to tell to not do ID/REFs registration.
* Used to initialize xmlLoadExtDtdDefaultValue in some special cases.
*/
#define XML_SKIP_IDS 8
/**
* xmlParserMode:
*
* A parser can operate in various modes
*/
typedef enum {
XML_PARSE_UNKNOWN = 0,
XML_PARSE_DOM = 1,
XML_PARSE_SAX = 2,
XML_PARSE_PUSH_DOM = 3,
XML_PARSE_PUSH_SAX = 4,
XML_PARSE_READER = 5
} xmlParserMode;
/**
* xmlParserCtxt:
*
* The parser context.
* NOTE This doesn't completely define the parser state, the (current ?)
* design of the parser uses recursive function calls since this allow
* and easy mapping from the production rules of the specification
* to the actual code. The drawback is that the actual function call
* also reflect the parser state. However most of the parsing routines
* takes as the only argument the parser context pointer, so migrating
* to a state based parser for progressive parsing shouldn't be too hard.
*/
struct _xmlParserCtxt {
struct _xmlSAXHandler *sax; /* The SAX handler */
void *userData; /* For SAX interface only, used by DOM build */
xmlDocPtr myDoc; /* the document being built */
int wellFormed; /* is the document well formed */
int replaceEntities; /* shall we replace entities ? */
const xmlChar *version; /* the XML version string */
const xmlChar *encoding; /* the declared encoding, if any */
int standalone; /* standalone document */
int html; /* an HTML(1)/Docbook(2) document
* 3 is HTML after <head>
* 10 is HTML after <body>
*/
/* Input stream stack */
xmlParserInputPtr input; /* Current input stream */
int inputNr; /* Number of current input streams */
int inputMax; /* Max number of input streams */
xmlParserInputPtr *inputTab; /* stack of inputs */
/* Node analysis stack only used for DOM building */
xmlNodePtr node; /* Current parsed Node */
int nodeNr; /* Depth of the parsing stack */
int nodeMax; /* Max depth of the parsing stack */
xmlNodePtr *nodeTab; /* array of nodes */
int record_info; /* Whether node info should be kept */
xmlParserNodeInfoSeq node_seq; /* info about each node parsed */
int errNo; /* error code */
int hasExternalSubset; /* reference and external subset */
int hasPErefs; /* the internal subset has PE refs */
int external; /* are we parsing an external entity */
int valid; /* is the document

我还在迷路
- 粉丝: 86
最新资源
- 本库是个基于python的工具集,用于记录数据到文件。 使用方便,代码简洁, 是一个可靠、省心且实用的工具。 支持多线程同时写入。.zip
- 本科毕业设计,基于python的图像复制粘贴篡改识别软件。.zip
- 本项目是基于计算机视觉的端到端交通路口智能监控系统.采用的设计架构由SRS
- 碧蓝航线ios平台自动脚本,基于python+opencv+facebook_wda实现.zip
- 毕业设计中基于给定微博数据的反作弊识别,用python开发。.zip
- 毕业设计项目,基于深度学习的实时语义分割算法研究,python实现。.zip
- 对基于python的微博爬虫进行重写,重写语言:java.zip
- 此框架是基于Python+Pytest+Requests+Allure+Yaml+Json实现全链路接口自动化测试
- 程序语言课程作业在线评测平台(实现Java、C、Python的选择、填空、代码题在线评测),基于SpringBoot+Layui+MySQL实现.zip
- 非官方的科大讯飞语音合成(用于朗读,配音场景)python API (基于官方demo增加了:超过2000字上限自动分割再合并音频的功能).zip
- 非官方的简易中国铁路列车运行图系统,基于Python + PyQt5
- 超市POS销售与后台管理系统_商品录入收银业务会员管理进货销售库存人员权限断网收银断电保护_实现超市前台POS销售商品扫描条形码输入收银计算找零打印清单会员折扣累计消费以及后台管理.zip
- 俄罗斯方块闯关版,基于Python实现.zip
- 该项目是基于Python和数据库实现的学生信息管理系统.zip
- 该仓库为agv系统调度软件的前后端实现。项目基于fastapi(python后端框架)和vue2实现了RESTful风格的前后端分离.zip
- 该项目是基于Scrapy框架的Python新闻爬虫,能够爬取网易,搜狐,凤凰和澎湃网站上的新闻,将标题,内容,评论,时间等内容整理并保存到本地.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈



评论26