From 6996c14f7b7ead06f8a38af8b62063e0165135a4 Mon Sep 17 00:00:00 2001
From: zhongrj <646384940@qq.com>
Date: Wed, 20 Mar 2024 10:21:02 +0800
Subject: [PATCH] test4j 优化
---
src/main/java/org/springblade/modules/test4j/Test4jController.java | 40 +++++++++++--
src/main/java/org/springblade/modules/test4j/util/Test4jUtil.java | 85 ++++++++++++++++++++++++++++
2 files changed, 119 insertions(+), 6 deletions(-)
diff --git a/src/main/java/org/springblade/modules/test4j/Test4jController.java b/src/main/java/org/springblade/modules/test4j/Test4jController.java
index 54ffb4a..7aced56 100644
--- a/src/main/java/org/springblade/modules/test4j/Test4jController.java
+++ b/src/main/java/org/springblade/modules/test4j/Test4jController.java
@@ -2,8 +2,11 @@
import io.swagger.annotations.Api;
import lombok.AllArgsConstructor;
+import net.sourceforge.tess4j.ITesseract;
import net.sourceforge.tess4j.Tesseract;
+import net.sourceforge.tess4j.TesseractException;
import org.springblade.core.tool.api.R;
+import org.springblade.modules.test4j.util.Test4jUtil;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RequestParam;
@@ -11,6 +14,11 @@
import org.springframework.web.multipart.MultipartFile;
import javax.imageio.ImageIO;
+import java.awt.*;
+import java.awt.image.BufferedImage;
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
@RestController
@AllArgsConstructor
@@ -20,17 +28,37 @@
@PostMapping("/read-id")
public R readText(@RequestParam("file") MultipartFile file) {
- // 在这里添加识别文本的代码，例如Tesseract OCR
- Tesseract tesseract = new Tesseract();
+ try {
+ BufferedImage grayscaleImage = grayscale(ImageIO.read(file.getInputStream()));
+ String text = recognizeText(grayscaleImage);
+ return R.data(text);
+ } catch (IOException e) {
+ e.printStackTrace();
+ return null;
+ }
+ }
+
+ public BufferedImage grayscale(BufferedImage image) {
+ int width = image.getWidth();
+ int height = image.getHeight();
+ BufferedImage result = new BufferedImage(width, height, BufferedImage.TYPE_BYTE_GRAY);
+ Graphics g = result.getGraphics();
+ g.drawImage(image, 0, 0, null);
+ g.dispose();
+ return result;
+ }
+
+ public String recognizeText(BufferedImage image) {
+ ITesseract tesseract = new Tesseract();
// 设置Tesseract的路径
tesseract.setDatapath("F:\\test4jdata");
// 设置为中文简体
tesseract.setLanguage("chi_sim");
try {
- String text = tesseract.doOCR(ImageIO.read(file.getInputStream()));
- return R.data(text);
- } catch (Exception e) {
- return R.data(e.getMessage());
+ return tesseract.doOCR(image);
+ } catch (TesseractException e) {
+ e.printStackTrace();
+ return null;
}
}
}
diff --git a/src/main/java/org/springblade/modules/test4j/util/Test4jUtil.java b/src/main/java/org/springblade/modules/test4j/util/Test4jUtil.java
new file mode 100644
index 0000000..40752e1
--- /dev/null
+++ b/src/main/java/org/springblade/modules/test4j/util/Test4jUtil.java
@@ -0,0 +1,85 @@
+package org.springblade.modules.test4j.util;
+
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+/**
+ * 身份证信息读取工具
+ */
+public class Test4jUtil {
+ /**
+ * 去掉字符串里的非中文字符
+ *
+ * @param inputString 字符串
+ * @return 中文字符串
+ */
+ public static String removeNonChinese(String inputString) {
+ // 匹配非汉字字符的正则表达式
+ String regex = "[^\u4E00-\u9FA5]";
+ Pattern pattern = Pattern.compile(regex);
+ Matcher matcher = pattern.matcher(inputString);
+ // 替换非汉字字符为空格
+ return matcher.replaceAll("");
+ }
+
+ /**
+ * 提取出生日期
+ *
+ * @param inputString 字符串
+ * @return 出生日期
+ */
+ private static String extractBirthDate(String inputString) {
+ // 匹配日期格式的正则表达式
+ String regex = "(\\d{4}年\\d{2}月\\d{2}日)";
+ Pattern pattern = Pattern.compile(regex);
+ Matcher matcher = pattern.matcher(inputString);
+ // 提取匹配到的日期
+ if (matcher.find()) {
+ return matcher.group(1);
+ } else {
+ return "未找到日期";
+ }
+ }
+
+ /**
+ * 截取指定字符
+ *
+ * @param inputString 字符串
+ * @param indexStart 开始Index
+ * @return 截取的字符串
+ */
+ public static String getStringByIndex(String inputString, int indexStart) {
+ return getStringByIndex(inputString, indexStart, -1);
+ }
+
+ /**
+ * 截取指定字符
+ *
+ * @param inputString 字符串
+ * @param indexStart 开始Index
+ * @param size 截取的字符个数
+ * @return 截取的字符串
+ */
+ public static String getStringByIndex(String inputString, int indexStart, int size) {
+ // 去除字符串两端的空白字符
+ String trimmedString = inputString.trim();
+ // 将字符串以空白字符分割
+ StringBuilder res = new StringBuilder();
+ String[] words = trimmedString.split("\\s+");
+ int length = words.length;
+ int contentSize = indexStart + size;
+ if (length > indexStart) {
+ int index = length;
+ if (size > 0 && length > contentSize) {
+ index = contentSize;
+ }
+ for (int i = indexStart; i < index; i++) {
+ res.append(words[i]);
+ }
+ }
+ return res.toString();
+ }
+
+
+
+}
--
Gitblit v1.9.3