htmlparser for chapter content

lib/Cargo.toml

@@ -8,20 +8,21 @@ repository = { workspace = true }
 readme = { workspace = true }
 keywords = { workspace = true }
 rust-version = { workspace = true }
+
 [dependencies]
-zip = "6.0.0"
+zip = "7.0.0"
 anyhow = "1.0.100"
-quick-xml = { version = "0.38.3" }
+quick-xml = { version = "0.38.4" }
 ab_glyph = { version = "0.2.32", optional = true }
-imageproc = { version = "0.25.0", optional = true}
-serde_json = { version = "1.0.145", optional = true }
+imageproc = { version = "0.26.0", optional = true}
+serde_json = { version = "1.0.149", optional = true }
 iepub-derive = { path = "../derive", version = "1.2.6" }
 serde = { version = "1.0.228", features = ["derive"], optional = true }
-image = { version = "0.25.8", default-features = false, features = ["jpeg"], optional = true }
+image = { version = "0.25.9", default-features = false, features = ["jpeg"], optional = true }
 md-5 = {version = "0.10.6", optional = true }
 
 [dev-dependencies]
-reqwest = { version = "0.11", features = ["blocking"] }
+reqwest = { version = "0.13.1", features = ["blocking"] }
 
 [features]
 no_nav=[]

lib/src/common.rs

@@ -139,6 +139,100 @@ impl From<FromUtf8Error> for IError {
         IError::Utf8(value)
     }
 }
+
+/// 内容类型枚举
+#[derive(Debug, Clone)]
+pub enum ContentType {
+    /// 段落
+    Paragraph,
+    /// 标题 (level: 1-6)
+    Heading(u8),
+    /// 图片
+    Image,
+    /// 链接
+    Link,
+    /// 列表项
+    ListItem,
+    /// 引用块
+    BlockQuote,
+    /// 代码块
+    CodeBlock,
+    /// 分隔线
+    HorizontalRule,
+    /// 普通文本
+    Text,
+    /// 其他标签
+    Other(String),
+}
+
+/// 解析后的内容项
+#[derive(Debug, Clone)]
+pub struct ContentItem {
+    /// 内容类型
+    pub content_type: ContentType,
+    /// 文本内容
+    pub text: String,
+    /// 属性 (例如图片的 src, 链接的 href 等)
+    pub attributes: Vec<(String, String)>,
+    /// 子内容
+    pub children: Vec<ContentItem>,
+}
+
+impl ContentItem {
+    pub fn new(content_type: ContentType) -> Self {
+        Self {
+            content_type,
+            text: String::new(),
+            attributes: Vec::new(),
+            children: Vec::new(),
+        }
+    }
+
+    /// 添加属性
+    pub fn add_attribute(&mut self, key: String, value: String) {
+        self.attributes.push((key, value));
+    }
+
+    /// 添加子内容
+    pub fn add_child(&mut self, child: ContentItem) {
+        self.children.push(child);
+    }
+
+    /// 添加文本
+    pub fn add_text(&mut self, text: &str) {
+        self.text.push_str(text);
+    }
+
+    /// 格式化输出
+    pub fn format(&self, indent: usize) -> String {
+        let indent_str = "  ".repeat(indent);
+        let mut result = format!("{}[{:?}]", indent_str, self.content_type);
+
+        if !self.text.is_empty() {
+            result.push_str(&format!(" 文本: \"{}\"", self.text.trim()));
+        }
+
+        if !self.attributes.is_empty() {
+            result.push_str(" 属性: {");
+            for (i, (key, value)) in self.attributes.iter().enumerate() {
+                if i > 0 {
+                    result.push_str(", ");
+                }
+                result.push_str(&format!("{}: \"{}\"", key, value));
+            }
+            result.push('}');
+        }
+
+        result.push('\n');
+
+        for child in &self.children {
+            result.push_str(&child.format(indent + 1));
+        }
+
+        result
+    }
+}
+
 cache_struct! {
     #[derive(Debug, Default)]
     pub(crate) struct BookInfo {

lib/src/epub/core.rs

@@ -9,6 +9,7 @@ use crate::cache_struct;
 use crate::common::{escape_xml, urldecode_enhanced, IError, IResult};
 use crate::epub::common::LinkRel;
 use crate::epub::html;
+use crate::parser::HtmlParser;
 crate::cache_enum! {
     #[derive(Clone)]
     pub enum Direction {
@@ -171,8 +172,11 @@ impl Debug for EpubHtml {
 }
 
 impl EpubHtml {
-    pub fn string_data(&self) -> String {
-        if let Some(data) = &self._data {
+    pub fn string_data(&mut self) -> String {
+        if self._data.is_none() {
+            self.data_mut();
+        }
+        if let Some(data) = &mut self._data {
             String::from_utf8(data.clone()).unwrap_or_else(|_e| String::new())
         } else {
             String::new()
@@ -183,6 +187,18 @@ impl EpubHtml {
         self._data.as_deref()
     }
 
+    pub fn parser(&mut self) -> Option<HtmlParser> {
+        let mut obj = None;
+        let html = self.string_data();
+        if !html.is_empty() {
+            let mut parser = HtmlParser::new();
+            if parser.parse(&html).is_ok() {
+                obj = Some(parser);
+            }
+        }
+        obj
+    }
+
     pub(crate) fn read_data(&mut self, reader: &mut impl EpubReaderTrait) {
         let (id, origin) = if let Some(index) = self._file_name.find('#') {
             (

lib/src/epub/reader.rs

@@ -1197,7 +1197,6 @@ html
         assert_ne!(0, nav.len());
         assert_ne!("", nav[0].title());
         let mut chap = book.chapters_mut();
-
         assert_eq!(75, chap.next().unwrap().data_mut().unwrap().len());
 
         // println!("{}", String::from_utf8( chap.next().unwrap().data().unwrap().to_vec()).unwrap());
@@ -1208,11 +1207,15 @@ html
             chap.next().unwrap().data_mut().unwrap().to_vec().len()
         );
 
+        for i in chap {
+            if let Some(p) = i.parser() {
+                assert_ne!(0, p.extract_plain_text().len());
+            }
+        }
         assert!(book.get_chapter("s04.xhtml#pgepubid00536").is_some());
         // assert!(chap.next().is_some());
         // chap.next();
         // chap.next();
-
         // assert_ne!("", chap.next().unwrap().title());
         // assert_ne!(None, book.chapters_mut().next().unwrap().data());
     }

lib/src/lib.rs

@@ -3,10 +3,11 @@
 #[allow(clippy::needless_range_loop)]
 extern crate iepub_derive;
 mod adapter;
-mod common;
+pub mod common;
 mod cover;
 mod epub;
 mod mobi;
+pub mod parser;
 pub mod path;
 pub use crate::common::DateTimeFormater;