添加golang版本
This commit is contained in:
liyanyan
parent
106ebc4c4a
commit
7878c7bee6
6
.gitignore
vendored
Normal file
6
.gitignore
vendored
Normal file
@ -0,0 +1,6 @@
|
||||
__pycache__
|
||||
output
|
||||
source
|
||||
执行结果记录_**.txt
|
||||
*.log
|
||||
*.exe
|
||||
140
README.md
Normal file
140
README.md
Normal file
@ -0,0 +1,140 @@
|
||||
# pdf-picker
|
||||
|
||||
基于 Go 的 PDF 回执拆分与分类工具。
|
||||
|
||||
功能说明：
|
||||
- 扫描输入目录中的 PDF 文件
|
||||
- 将回执按页面内多条回执进行拆分并导出图片
|
||||
- 从文本中提取“收款人全称”并按名称分类到输出目录
|
||||
- 识别失败时可使用 OCR 兜底
|
||||
- 生成执行结果记录文件（含每个 PDF 的目录与图片明细）
|
||||
|
||||
## 1. 项目结构
|
||||
|
||||
- index.go: Go 主程序
|
||||
- go.mod / go.sum: Go 模块依赖
|
||||
- source/: 默认输入目录（放 PDF）
|
||||
- output/: 默认输出目录（分类后的图片）
|
||||
|
||||
## 2. 运行环境
|
||||
|
||||
- Windows
|
||||
- Go 1.19+
|
||||
- C 编译器（用于 cgo，go-fitz 依赖）
|
||||
- 可选：Tesseract OCR（用于识别扫描件）
|
||||
|
||||
当前项目依赖：
|
||||
- github.com/gen2brain/go-fitz v1.20.2
|
||||
|
||||
## 3. 工具链配置（Windows）
|
||||
|
||||
如果构建时报错 `gcc not found`，可使用 LLVM-MinGW。
|
||||
|
||||
示例（已验证可用路径）：
|
||||
|
||||
1) 安装 LLVM-MinGW（任选一种）
|
||||
- 使用 winget
|
||||
- 手动下载并解压到 C:/llvm-mingw
|
||||
|
||||
2) 配置 Go 使用 clang 作为 cgo 编译器（PowerShell）
|
||||
|
||||
```powershell
|
||||
go env -w CC="C:\llvm-mingw\llvm-mingw-20260519-ucrt-x86_64\bin\clang.exe"
|
||||
go env -w CXX="C:\llvm-mingw\llvm-mingw-20260519-ucrt-x86_64\bin\clang++.exe"
|
||||
go env -w CGO_ENABLED=1
|
||||
```
|
||||
|
||||
3) 检查配置
|
||||
|
||||
```powershell
|
||||
go env CC CXX CGO_ENABLED
|
||||
```
|
||||
|
||||
## 4. 编译
|
||||
|
||||
```powershell
|
||||
go mod tidy
|
||||
go build index.go
|
||||
```
|
||||
|
||||
编译成功后会生成可执行文件：
|
||||
- index.exe
|
||||
|
||||
## 5. 运行
|
||||
|
||||
### 5.1 默认目录
|
||||
|
||||
```powershell
|
||||
.\index.exe
|
||||
```
|
||||
|
||||
等价于：
|
||||
- 输入目录：./source
|
||||
- 输出目录：./output
|
||||
|
||||
### 5.2 指定目录（短参数）
|
||||
|
||||
```powershell
|
||||
.\index.exe -i ./source -o ./output2
|
||||
```
|
||||
|
||||
### 5.3 指定目录（位置参数）
|
||||
|
||||
```powershell
|
||||
.\index.exe ./source ./output2
|
||||
```
|
||||
|
||||
优先级：
|
||||
- 命名参数（-i/-o 或 --input/--output）
|
||||
- 位置参数
|
||||
- 默认目录（source/output）
|
||||
|
||||
## 6. 输出结果
|
||||
|
||||
运行结束后会看到控制台统计，并在项目根目录生成记录文件：
|
||||
|
||||
- 执行结果记录_YYYYMMDD_HHMMSS.txt
|
||||
|
||||
记录内容包括：
|
||||
- 每个 PDF 拆分目录数
|
||||
- 每个目录对应图片数量
|
||||
- 识别成功/失败数量
|
||||
- 全部汇总
|
||||
|
||||
## 7. OCR 说明
|
||||
|
||||
程序在文本提取失败时会尝试调用：
|
||||
|
||||
```text
|
||||
tesseract <image> stdout -l chi_sim+eng
|
||||
```
|
||||
|
||||
如果本机未安装 tesseract，OCR 兜底会自动跳过，不影响程序主流程（但扫描件识别率会下降）。
|
||||
|
||||
## 8. 常见问题
|
||||
|
||||
### Q1: 构建时报 `gcc not found`
|
||||
|
||||
原因：缺少 cgo 编译器。
|
||||
处理：按第 3 节安装并配置 LLVM-MinGW。
|
||||
|
||||
### Q2: 构建时出现大量 `ld.lld: warning: duplicate symbol`
|
||||
|
||||
这是链接阶段警告，若最终退出码为 0 且生成 index.exe，可继续使用。
|
||||
|
||||
### Q3: 没有识别出“收款人全称”
|
||||
|
||||
- 可能是 PDF 为扫描件且 OCR 不可用
|
||||
- 可能是单据模板字段格式与当前规则不一致
|
||||
|
||||
可通过增强正则规则或补充 OCR 环境提升识别率。
|
||||
|
||||
## 9. 快速开始
|
||||
|
||||
```powershell
|
||||
# 1) 放入 PDF 到 source
|
||||
# 2) 编译
|
||||
go build index.go
|
||||
# 3) 运行
|
||||
.\index.exe -o ./output2
|
||||
```
|
||||
5
go.mod
Normal file
5
go.mod
Normal file
@ -0,0 +1,5 @@
|
||||
module pdf-picker
|
||||
|
||||
go 1.19
|
||||
|
||||
require github.com/gen2brain/go-fitz v1.20.2
|
||||
2
go.sum
Normal file
2
go.sum
Normal file
@ -0,0 +1,2 @@
|
||||
github.com/gen2brain/go-fitz v1.20.2 h1:4FPJCU/ImQ32oojBsYn/+oTkRORxbAhAA+Yw1Fm97MA=
|
||||
github.com/gen2brain/go-fitz v1.20.2/go.mod h1:YbQPODTC/UnQ/RK4JyD3zfpDQ19UKiV85nMMT3XpT0s=
|
||||
418
index.go
Normal file
418
index.go
Normal file
@ -0,0 +1,418 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"flag"
|
||||
"fmt"
|
||||
"image"
|
||||
"image/png"
|
||||
"os"
|
||||
"os/exec"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
fitz "github.com/gen2brain/go-fitz"
|
||||
)
|
||||
|
||||
const receiptHeader = "中国建设银行网上银行电子回执"
|
||||
|
||||
type processResult struct {
|
||||
SuccessCount int
|
||||
FailedCount int
|
||||
PerDirCounts map[string]int
|
||||
}
|
||||
|
||||
var (
|
||||
invalidPathChars = regexp.MustCompile(`[\\/:*?"<>|]`)
|
||||
spacePattern = regexp.MustCompile(`\s+`)
|
||||
payeeStopPattern = regexp.MustCompile(`别名|账号|开户行|大写金额|小写金额|用途|钞汇标志|摘要|重要提示|付款人全称`)
|
||||
)
|
||||
|
||||
func safeDirName(name string) string {
|
||||
cleaned := invalidPathChars.ReplaceAllString(strings.TrimSpace(name), "_")
|
||||
cleaned = spacePattern.ReplaceAllString(cleaned, " ")
|
||||
if cleaned == "" {
|
||||
return "未识别收款人"
|
||||
}
|
||||
if len([]rune(cleaned)) > 120 {
|
||||
return string([]rune(cleaned)[:120])
|
||||
}
|
||||
return cleaned
|
||||
}
|
||||
|
||||
func extractPayeeName(text string) string {
|
||||
if strings.TrimSpace(text) == "" {
|
||||
return ""
|
||||
}
|
||||
|
||||
normalized := strings.ReplaceAll(text, "\u3000", " ")
|
||||
compact := spacePattern.ReplaceAllString(normalized, "")
|
||||
|
||||
if idx := strings.Index(compact, "收款人全称"); idx >= 0 {
|
||||
tail := strings.TrimLeft(compact[idx+len("收款人全称"):], ":：")
|
||||
if tail != "" {
|
||||
if stop := payeeStopPattern.FindStringIndex(tail); stop != nil && stop[0] > 0 {
|
||||
tail = tail[:stop[0]]
|
||||
}
|
||||
tail = strings.Trim(tail, " :：")
|
||||
if tail != "" {
|
||||
return tail
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
patterns := []string{
|
||||
`收款人全称\s*[:：]\s*([^\n\r]+)`,
|
||||
`收款人\s*全称\s*[:：]\s*([^\n\r]+)`,
|
||||
`收\s*款\s*人\s*全\s*称\s*[:：]?\s*([^\n\r]+)`,
|
||||
`收款人全称\s+([^\n\r]+)`,
|
||||
}
|
||||
for _, p := range patterns {
|
||||
re := regexp.MustCompile(p)
|
||||
match := re.FindStringSubmatch(normalized)
|
||||
if len(match) > 1 {
|
||||
value := strings.TrimSpace(match[1])
|
||||
cutRe := regexp.MustCompile(`\s{2,}|金额|开户行|账号|日期`)
|
||||
value = strings.Trim(cutRe.Split(value, 2)[0], " :：")
|
||||
if value != "" {
|
||||
return value
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
lines := strings.Split(normalized, "\n")
|
||||
filtered := make([]string, 0, len(lines))
|
||||
for _, line := range lines {
|
||||
line = strings.TrimSpace(line)
|
||||
if line != "" {
|
||||
filtered = append(filtered, line)
|
||||
}
|
||||
}
|
||||
for i, line := range filtered {
|
||||
if strings.Contains(line, "收款人全称") {
|
||||
after := strings.Trim(strings.SplitN(line, "收款人全称", 2)[1], " :：")
|
||||
if after != "" {
|
||||
return after
|
||||
}
|
||||
if i+1 < len(filtered) {
|
||||
candidate := strings.Trim(filtered[i+1], " :：")
|
||||
if candidate != "" {
|
||||
return candidate
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return ""
|
||||
}
|
||||
|
||||
func extractTextViaOCR(imagePath string) string {
|
||||
cmd := exec.Command("tesseract", imagePath, "stdout", "-l", "chi_sim+eng")
|
||||
var out bytes.Buffer
|
||||
cmd.Stdout = &out
|
||||
cmd.Stderr = nil
|
||||
if err := cmd.Run(); err != nil {
|
||||
return ""
|
||||
}
|
||||
return out.String()
|
||||
}
|
||||
|
||||
func cropImage(src image.Image, rect image.Rectangle) image.Image {
|
||||
rgba := image.NewRGBA(image.Rect(0, 0, rect.Dx(), rect.Dy()))
|
||||
for y := rect.Min.Y; y < rect.Max.Y; y++ {
|
||||
for x := rect.Min.X; x < rect.Max.X; x++ {
|
||||
rgba.Set(x-rect.Min.X, y-rect.Min.Y, src.At(x, y))
|
||||
}
|
||||
}
|
||||
return rgba
|
||||
}
|
||||
|
||||
func splitPageTextByHeader(pageText string) []string {
|
||||
if strings.TrimSpace(pageText) == "" {
|
||||
return []string{""}
|
||||
}
|
||||
count := strings.Count(pageText, receiptHeader)
|
||||
if count <= 1 {
|
||||
return []string{pageText}
|
||||
}
|
||||
|
||||
parts := strings.Split(pageText, receiptHeader)
|
||||
segments := make([]string, 0, count)
|
||||
for i := 1; i < len(parts); i++ {
|
||||
segments = append(segments, receiptHeader+parts[i])
|
||||
}
|
||||
if len(segments) == 0 {
|
||||
return []string{pageText}
|
||||
}
|
||||
return segments
|
||||
}
|
||||
|
||||
func splitPageImageByHeaderCount(img image.Image, count int) []image.Image {
|
||||
b := img.Bounds()
|
||||
if count <= 1 {
|
||||
return []image.Image{img}
|
||||
}
|
||||
height := b.Dy()
|
||||
width := b.Dx()
|
||||
segments := make([]image.Image, 0, count)
|
||||
for i := 0; i < count; i++ {
|
||||
y0 := b.Min.Y + (height*i)/count
|
||||
y1 := b.Min.Y + (height*(i+1))/count
|
||||
if y1 <= y0 {
|
||||
continue
|
||||
}
|
||||
rect := image.Rect(b.Min.X, y0, b.Min.X+width, y1)
|
||||
segments = append(segments, cropImage(img, rect))
|
||||
}
|
||||
if len(segments) == 0 {
|
||||
return []image.Image{img}
|
||||
}
|
||||
return segments
|
||||
}
|
||||
|
||||
func processPDF(pdfPath, outputDir string) (processResult, error) {
|
||||
res := processResult{PerDirCounts: map[string]int{}}
|
||||
|
||||
doc, err := fitz.New(pdfPath)
|
||||
if err != nil {
|
||||
return res, err
|
||||
}
|
||||
defer doc.Close()
|
||||
|
||||
totalPages := doc.NumPage()
|
||||
for pageIndex := 0; pageIndex < totalPages; pageIndex++ {
|
||||
pageText, textErr := doc.Text(pageIndex)
|
||||
if textErr != nil {
|
||||
pageText = ""
|
||||
}
|
||||
|
||||
headerCount := strings.Count(pageText, receiptHeader)
|
||||
if headerCount <= 0 {
|
||||
headerCount = 1
|
||||
}
|
||||
|
||||
img, imgErr := doc.ImageDPI(pageIndex, 200)
|
||||
if imgErr != nil {
|
||||
return res, imgErr
|
||||
}
|
||||
|
||||
imgSegments := splitPageImageByHeaderCount(img, headerCount)
|
||||
textSegments := splitPageTextByHeader(pageText)
|
||||
|
||||
for i, segment := range imgSegments {
|
||||
receiptIndex := i + 1
|
||||
imageName := fmt.Sprintf("%s_p%03d_r%03d.png", strings.TrimSuffix(filepath.Base(pdfPath), filepath.Ext(pdfPath)), pageIndex+1, receiptIndex)
|
||||
tempImagePath := filepath.Join(outputDir, imageName)
|
||||
|
||||
f, createErr := os.Create(tempImagePath)
|
||||
if createErr != nil {
|
||||
return res, createErr
|
||||
}
|
||||
encodeErr := png.Encode(f, segment)
|
||||
closeErr := f.Close()
|
||||
if encodeErr != nil {
|
||||
return res, encodeErr
|
||||
}
|
||||
if closeErr != nil {
|
||||
return res, closeErr
|
||||
}
|
||||
|
||||
receiptText := pageText
|
||||
if i < len(textSegments) {
|
||||
receiptText = textSegments[i]
|
||||
}
|
||||
payeeName := extractPayeeName(receiptText)
|
||||
|
||||
if payeeName == "" {
|
||||
ocrText := extractTextViaOCR(tempImagePath)
|
||||
payeeName = extractPayeeName(ocrText)
|
||||
}
|
||||
|
||||
if payeeName == "" {
|
||||
payeeName = "未识别收款人"
|
||||
res.FailedCount++
|
||||
} else {
|
||||
res.SuccessCount++
|
||||
}
|
||||
|
||||
targetDirName := safeDirName(payeeName)
|
||||
targetDir := filepath.Join(outputDir, targetDirName)
|
||||
if mkErr := os.MkdirAll(targetDir, os.ModePerm); mkErr != nil {
|
||||
return res, mkErr
|
||||
}
|
||||
res.PerDirCounts[targetDirName]++
|
||||
|
||||
finalImagePath := filepath.Join(targetDir, imageName)
|
||||
if _, statErr := os.Stat(finalImagePath); statErr == nil {
|
||||
finalImagePath = filepath.Join(targetDir,
|
||||
fmt.Sprintf("%s_p%03d_r%03d_%d.png", strings.TrimSuffix(filepath.Base(pdfPath), filepath.Ext(pdfPath)), pageIndex+1, receiptIndex, os.Getpid()))
|
||||
}
|
||||
|
||||
if renameErr := os.Rename(tempImagePath, finalImagePath); renameErr != nil {
|
||||
return res, renameErr
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return res, nil
|
||||
}
|
||||
|
||||
func writeExecutionReport(baseDir string, lines []string) (string, error) {
|
||||
timestamp := time.Now().Format("20060102_150405")
|
||||
reportPath := filepath.Join(baseDir, fmt.Sprintf("执行结果记录_%s.txt", timestamp))
|
||||
content := strings.Join(lines, "\n") + "\n"
|
||||
if err := os.WriteFile(reportPath, []byte(content), 0o644); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return reportPath, nil
|
||||
}
|
||||
|
||||
func resolveIODirs(baseDir string) (string, string) {
|
||||
defaultSourceDir := filepath.Join(baseDir, "source")
|
||||
defaultOutputDir := filepath.Join(baseDir, "output")
|
||||
|
||||
inputOpt := flag.String("input", "", "输入目录")
|
||||
outputOpt := flag.String("output", "", "输出目录")
|
||||
inputShort := flag.String("i", "", "输入目录")
|
||||
outputShort := flag.String("o", "", "输出目录")
|
||||
flag.Parse()
|
||||
|
||||
args := flag.Args()
|
||||
posInput := ""
|
||||
posOutput := ""
|
||||
if len(args) >= 1 {
|
||||
posInput = args[0]
|
||||
}
|
||||
if len(args) >= 2 {
|
||||
posOutput = args[1]
|
||||
}
|
||||
|
||||
inputRaw := firstNonEmpty(*inputOpt, *inputShort, posInput)
|
||||
outputRaw := firstNonEmpty(*outputOpt, *outputShort, posOutput)
|
||||
|
||||
sourceDir := defaultSourceDir
|
||||
if inputRaw != "" {
|
||||
sourceDir = inputRaw
|
||||
}
|
||||
outputDir := defaultOutputDir
|
||||
if outputRaw != "" {
|
||||
outputDir = outputRaw
|
||||
}
|
||||
|
||||
sourceAbs, _ := filepath.Abs(sourceDir)
|
||||
outputAbs, _ := filepath.Abs(outputDir)
|
||||
return sourceAbs, outputAbs
|
||||
}
|
||||
|
||||
func firstNonEmpty(values ...string) string {
|
||||
for _, v := range values {
|
||||
if strings.TrimSpace(v) != "" {
|
||||
return v
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func main() {
|
||||
baseDir, wdErr := os.Getwd()
|
||||
if wdErr != nil {
|
||||
fmt.Printf("获取当前目录失败: %v\n", wdErr)
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
sourceDir, outputDir := resolveIODirs(baseDir)
|
||||
if err := os.MkdirAll(sourceDir, os.ModePerm); err != nil {
|
||||
fmt.Printf("创建输入目录失败: %v\n", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
if err := os.MkdirAll(outputDir, os.ModePerm); err != nil {
|
||||
fmt.Printf("创建输出目录失败: %v\n", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
entries, readErr := os.ReadDir(sourceDir)
|
||||
if readErr != nil {
|
||||
fmt.Printf("读取输入目录失败: %v\n", readErr)
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
pdfFiles := make([]string, 0)
|
||||
for _, e := range entries {
|
||||
if e.IsDir() {
|
||||
continue
|
||||
}
|
||||
if strings.EqualFold(filepath.Ext(e.Name()), ".pdf") {
|
||||
pdfFiles = append(pdfFiles, filepath.Join(sourceDir, e.Name()))
|
||||
}
|
||||
}
|
||||
sort.Strings(pdfFiles)
|
||||
|
||||
if len(pdfFiles) == 0 {
|
||||
fmt.Printf("未在目录中发现 PDF: %s\n", sourceDir)
|
||||
fmt.Println("请将 PDF 文件放到 source 目录后重试。")
|
||||
return
|
||||
}
|
||||
|
||||
totalOK := 0
|
||||
totalUnknown := 0
|
||||
reportLines := []string{
|
||||
fmt.Sprintf("执行时间: %s", time.Now().Format("2006-01-02 15:04:05")),
|
||||
fmt.Sprintf("输入目录: %s", sourceDir),
|
||||
fmt.Sprintf("输出目录: %s", outputDir),
|
||||
"",
|
||||
}
|
||||
|
||||
for _, pdfPath := range pdfFiles {
|
||||
fmt.Printf("处理文件: %s\n", filepath.Base(pdfPath))
|
||||
res, err := processPDF(pdfPath, outputDir)
|
||||
if err != nil {
|
||||
fmt.Printf(" 处理失败: %v\n", err)
|
||||
continue
|
||||
}
|
||||
|
||||
fmt.Printf(" 识别到收款人全称的图片数: %d\n", res.SuccessCount)
|
||||
fmt.Printf(" 未识别收款人全称的图片数: %d\n", res.FailedCount)
|
||||
|
||||
totalOK += res.SuccessCount
|
||||
totalUnknown += res.FailedCount
|
||||
|
||||
reportLines = append(reportLines,
|
||||
fmt.Sprintf("PDF: %s", filepath.Base(pdfPath)),
|
||||
fmt.Sprintf(" 拆分目录数: %d", len(res.PerDirCounts)),
|
||||
fmt.Sprintf(" 识别到收款人全称的图片数: %d", res.SuccessCount),
|
||||
fmt.Sprintf(" 未识别收款人全称的图片数: %d", res.FailedCount),
|
||||
" 目录明细:",
|
||||
)
|
||||
|
||||
dirNames := make([]string, 0, len(res.PerDirCounts))
|
||||
for dir := range res.PerDirCounts {
|
||||
dirNames = append(dirNames, dir)
|
||||
}
|
||||
sort.Strings(dirNames)
|
||||
for _, dir := range dirNames {
|
||||
reportLines = append(reportLines, fmt.Sprintf(" - %s: %d 张", dir, res.PerDirCounts[dir]))
|
||||
}
|
||||
reportLines = append(reportLines, "")
|
||||
}
|
||||
|
||||
fmt.Println("\n处理完成")
|
||||
fmt.Printf("识别到收款人全称的图片数: %d\n", totalOK)
|
||||
fmt.Printf("未识别收款人全称的图片数: %d\n", totalUnknown)
|
||||
fmt.Printf("输出目录: %s\n", outputDir)
|
||||
|
||||
reportLines = append(reportLines,
|
||||
"汇总:",
|
||||
fmt.Sprintf(" 识别到收款人全称的图片总数: %d", totalOK),
|
||||
fmt.Sprintf(" 未识别收款人全称的图片总数: %d", totalUnknown),
|
||||
)
|
||||
|
||||
reportPath, err := writeExecutionReport(baseDir, reportLines)
|
||||
if err != nil {
|
||||
fmt.Printf("写入执行结果记录失败: %v\n", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
fmt.Printf("执行结果记录文件: %s\n", reportPath)
|
||||
}
|
||||
Loading…
x
Reference in New Issue
Block a user