init: WordFileParse docx→HTML 解析服务（含 Word EQ 域公式修复）
服务：Spring Boot 3.2 + docx4j 8.3.9，POST /api/v3/server_office_file/file/parse
接受 .docx，返回 HTML（公式 → LaTeX，图片 → RustFS 外链）
公式支持三类来源：
- OMML（Word 2007+ 公式） → Python omml_mathml2latex
- MathType OLE 对象 → Ruby mathtype2mathml → MathML → LaTeX
- Word EQ 域（老教辅主力） → EqToLatexUtil（本次新增）
本次改动：
1. 新增 java-svc/.../core/EqToLatexUtil.java：
移植自 jby backend-services office-core，EQ 语法 → LaTeX
（\f→\dfrac、\r→\sqrt、\i→\int/\sum/\prod、\s→^{}/_{}、\b→\left\right、
\a→array、\x→\boxed/\overline、\o\al 堆叠、圈码、化学符号、极限、连等式）
品牌标记 JBYU* → WPU*，与采集端一致
2. CtoMathFinder：接上 EQ 分支（原为 not-ported 桩），域代码经
EqToLatexUtil.convert 转 LaTeX 写入 eqLatexMap（WPEQNUM 占位符）
3. WordParseUtil.dealPlaceholder：EQ 的 LaTeX 同样加 \( \) 包裹
（原先因 WPEQNUM 例外不加包裹，前端/MathJax 不渲染）
修前症状：教辅 Word 里分式/方程组/上下标整段丢失（如 {−1/3, 1} 变成 {－，1}）
修后实测：46 份教辅 2908 处 EQ 域全部还原，公式总数 2954 处、零未包裹残留
安全：application.yml（含 RustFS 密钥）不入库，提供 application.yml.example；
OssService 的 @Value 默认密钥已清空
This commit is contained in:
136
java-svc/pom.xml
Normal file
136
java-svc/pom.xml
Normal file
@@ -0,0 +1,136 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project xmlns="http://maven.apache.org/POM/4.0.0"
|
||||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
|
||||
<modelVersion>4.0.0</modelVersion>
|
||||
|
||||
<parent>
|
||||
<groupId>org.springframework.boot</groupId>
|
||||
<artifactId>spring-boot-starter-parent</artifactId>
|
||||
<version>3.2.5</version>
|
||||
</parent>
|
||||
|
||||
<groupId>com.wordparse</groupId>
|
||||
<artifactId>word-file-parse</artifactId>
|
||||
<version>1.0.0</version>
|
||||
<packaging>jar</packaging>
|
||||
<name>WordFileParse</name>
|
||||
|
||||
<properties>
|
||||
<java.version>17</java.version>
|
||||
<docx4j.version>8.3.9</docx4j.version>
|
||||
</properties>
|
||||
|
||||
<dependencies>
|
||||
<!-- Spring Boot Web -->
|
||||
<dependency>
|
||||
<groupId>org.springframework.boot</groupId>
|
||||
<artifactId>spring-boot-starter-web</artifactId>
|
||||
</dependency>
|
||||
|
||||
<!-- Lombok -->
|
||||
<dependency>
|
||||
<groupId>org.projectlombok</groupId>
|
||||
<artifactId>lombok</artifactId>
|
||||
<optional>true</optional>
|
||||
</dependency>
|
||||
|
||||
<!-- Docx4J 8.x (Word → HTML) -->
|
||||
<dependency>
|
||||
<groupId>org.docx4j</groupId>
|
||||
<artifactId>docx4j-core</artifactId>
|
||||
<version>${docx4j.version}</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.docx4j</groupId>
|
||||
<artifactId>docx4j-JAXB-ReferenceImpl</artifactId>
|
||||
<version>${docx4j.version}</version>
|
||||
</dependency>
|
||||
|
||||
<!-- Jsoup (HTML post-processing) -->
|
||||
<dependency>
|
||||
<groupId>org.jsoup</groupId>
|
||||
<artifactId>jsoup</artifactId>
|
||||
<version>1.17.2</version>
|
||||
</dependency>
|
||||
|
||||
<!-- Apache Commons -->
|
||||
<dependency>
|
||||
<groupId>org.apache.commons</groupId>
|
||||
<artifactId>commons-lang3</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.commons</groupId>
|
||||
<artifactId>commons-collections4</artifactId>
|
||||
<version>4.4</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>commons-io</groupId>
|
||||
<artifactId>commons-io</artifactId>
|
||||
<version>2.16.1</version>
|
||||
</dependency>
|
||||
|
||||
<!-- FastJSON -->
|
||||
<dependency>
|
||||
<groupId>com.alibaba</groupId>
|
||||
<artifactId>fastjson</artifactId>
|
||||
<version>2.0.51</version>
|
||||
</dependency>
|
||||
|
||||
<!-- AWS S3 SDK (RustFS) -->
|
||||
<dependency>
|
||||
<groupId>software.amazon.awssdk</groupId>
|
||||
<artifactId>s3</artifactId>
|
||||
<version>2.25.27</version>
|
||||
</dependency>
|
||||
|
||||
|
||||
<dependency>
|
||||
<groupId>org.glassfish.jaxb</groupId>
|
||||
<artifactId>jaxb-runtime</artifactId>
|
||||
<version>2.3.1</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>net.sf.saxon</groupId>
|
||||
<artifactId>Saxon-HE</artifactId>
|
||||
<version>12.5</version>
|
||||
</dependency>
|
||||
|
||||
<!-- ImageIO for TIFF handling -->
|
||||
<dependency>
|
||||
<groupId>com.twelvemonkeys.imageio</groupId>
|
||||
<artifactId>imageio-tiff</artifactId>
|
||||
<version>3.11.0</version>
|
||||
</dependency>
|
||||
</dependencies>
|
||||
|
||||
<build>
|
||||
<plugins>
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-compiler-plugin</artifactId>
|
||||
<configuration>
|
||||
<annotationProcessorPaths>
|
||||
<path>
|
||||
<groupId>org.projectlombok</groupId>
|
||||
<artifactId>lombok</artifactId>
|
||||
<version>1.18.32</version>
|
||||
</path>
|
||||
</annotationProcessorPaths>
|
||||
</configuration>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>org.springframework.boot</groupId>
|
||||
<artifactId>spring-boot-maven-plugin</artifactId>
|
||||
<configuration>
|
||||
<excludes>
|
||||
<exclude>
|
||||
<groupId>org.projectlombok</groupId>
|
||||
<artifactId>lombok</artifactId>
|
||||
</exclude>
|
||||
</excludes>
|
||||
</configuration>
|
||||
</plugin>
|
||||
</plugins>
|
||||
</build>
|
||||
</project>
|
||||
Reference in New Issue
Block a user