Improve library

Author: ledongthuc

.github/workflows/ci.yml

@@ -0,0 +1,29 @@
+name: Go CI
+
+on:
+  push:
+    branches: [ "*" ]
+  pull_request:
+    branches: [ "*" ]
+
+jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Go
+      uses: actions/setup-go@v5
+      with:
+        go-version: '1.24'
+        cache: true
+
+    - name: Install dependencies
+      run: go mod download
+
+    - name: Run tests
+      run: go test -v ./...
+
+    - name: Build
+      run: go build -v ./... 

README.md

@@ -12,6 +12,10 @@ Features
 
 `go get -u github.com/ledongthuc/pdf`
 
+## Examples:
+
+ - Check in examples/ folder
+
 
 ## Read plain text
 
@@ -27,60 +31,56 @@ import (
 
 func main() {
 	pdf.DebugOn = true
-	content, err := readPdf("test.pdf") // Read local pdf file
+
+	f, r, err := pdf.Open("./pdf_test.pdf")
 	if err != nil {
 		panic(err)
 	}
-	fmt.Println(content)
-	return
-}
+	defer f.Close()
 
-func readPdf(path string) (string, error) {
-	f, r, err := pdf.Open(path)
-	// remember close file
-    defer f.Close()
+	var buf bytes.Buffer
+	b, err := r.GetPlainText()
 	if err != nil {
-		return "", err
+		panic(err)
 	}
-	var buf bytes.Buffer
-    b, err := r.GetPlainText()
-    if err != nil {
-        return "", err
-    }
-    buf.ReadFrom(b)
-	return buf.String(), nil
+	buf.ReadFrom(b)
+	content := buf.String()
+	fmt.Println(content)
 }
 ```
 
 ## Read all text with styles from PDF
 
 ```golang
-func readPdf2(path string) (string, error) {
-	f, r, err := pdf.Open(path)
-	// remember close file
+package main
+
+import (
+	"fmt"
+
+	"github.com/ledongthuc/pdf"
+)
+
+func main() {
+	f, r, err := pdf.Open("./pdf_test.pdf")
+	if err != nil {
+		panic(err)
+	}
 	defer f.Close()
+
+	sentences, err := r.GetStyledTexts()
 	if err != nil {
-		return "", err
+		panic(err)
 	}
-	totalPage := r.NumPage()
 
-	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
-		p := r.Page(pageIndex)
-		if p.V.IsNull() {
-			continue
-		}
-		var lastTextStyle pdf.Text
-		texts := p.Content().Text
-		for _, text := range texts {
-			if isSameSentence(text, lastTextStyle) {
-				lastTextStyle.S = lastTextStyle.S + text.S
-			} else {
-				fmt.Printf("Font: %s, Font-size: %f, x: %f, y: %f, content: %s \n", lastTextStyle.Font, lastTextStyle.FontSize, lastTextStyle.X, lastTextStyle.Y, lastTextStyle.S)
-				lastTextStyle = text
-			}
-		}
+	// Print all sentences
+	for _, sentence := range sentences {
+		fmt.Printf("Font: %s, Font-size: %f, x: %f, y: %f, content: %s \n",
+			sentence.Font,
+			sentence.FontSize,
+			sentence.X,
+			sentence.Y,
+			sentence.S)
 	}
-	return "", nil
 }
 ```
 

examples/read_plain_text/main.go

@@ -0,0 +1,27 @@
+package main
+
+import (
+	"bytes"
+	"fmt"
+
+	"github.com/ledongthuc/pdf"
+)
+
+func main() {
+	pdf.DebugOn = true
+
+	f, r, err := pdf.Open("./pdf_test.pdf")
+	if err != nil {
+		panic(err)
+	}
+	defer f.Close()
+
+	var buf bytes.Buffer
+	b, err := r.GetPlainText()
+	if err != nil {
+		panic(err)
+	}
+	buf.ReadFrom(b)
+	content := buf.String()
+	fmt.Println(content)
+}

examples/read_plain_text/pdf_test.pdf

@@ -0,0 +1,30 @@
+package main
+
+import (
+	"fmt"
+
+	"github.com/ledongthuc/pdf"
+)
+
+func main() {
+	f, r, err := pdf.Open("./pdf_test.pdf")
+	if err != nil {
+		panic(err)
+	}
+	defer f.Close()
+
+	sentences, err := r.GetStyledTexts()
+	if err != nil {
+		panic(err)
+	}
+
+	// Print all sentences
+	for _, sentence := range sentences {
+		fmt.Printf("Font: %s, Font-size: %f, x: %f, y: %f, content: %s \n",
+			sentence.Font,
+			sentence.FontSize,
+			sentence.X,
+			sentence.Y,
+			sentence.S)
+	}
+}

examples/read_text_with_styles/main.go

@@ -0,0 +1,3 @@
+module github.com/ledongthuc/pdf
+
+go 1.24.1

examples/read_text_with_styles/pdf_test.pdf

@@ -82,6 +82,37 @@ func (r *Reader) GetPlainText() (reader io.Reader, err error) {
 	return &buf, nil
 }
 
+// GetStyledTexts returns list all sentences in an array, that are included styles
+func (r *Reader) GetStyledTexts() (sentences []Text, err error) {
+	totalPage := r.NumPage()
+	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
+		p := r.Page(pageIndex)
+		if p.V.IsNull() {
+			continue
+		}
+		var lastTextStyle Text
+		texts := p.Content().Text
+		for _, text := range texts {
+			if lastTextStyle == (Text{}) {
+				lastTextStyle = text
+				continue
+			}
+
+			if IsSameSentence(lastTextStyle, text) {
+				lastTextStyle.S = lastTextStyle.S + text.S
+			} else {
+				sentences = append(sentences, lastTextStyle)
+				lastTextStyle = text
+			}
+		}
+		if len(lastTextStyle.S) > 0 {
+			sentences = append(sentences, lastTextStyle)
+		}
+	}
+
+	return sentences, err
+}
+
 func (p Page) findInherited(key string) Value {
 	for v := p.V; !v.IsNull(); v = v.Key("Parent") {
 		if r := v.Key(key); !r.IsNull() {
@@ -524,6 +555,8 @@ func (p Page) GetPlainText(fonts map[string]*Font) (result string, err error) {
 
 		switch op {
 		default:
+			// Easier debug
+			// fmt.Println("<DEBUG><op>", op, "</op><args>", args, "</args>")
 			return
 		case "T*": // move to start of next line
 			showText("\n")

go.mod

@@ -6,7 +6,6 @@ package pdf
 
 import (
 	"math"
-	"strings"
 	"unicode"
 	"unicode/utf16"
 )
@@ -162,10 +161,9 @@ var macRomanEncoding = [256]rune{
 // isSameSentence checks if the current text segment likely belongs to the same sentence
 // as the last text segment based on font, size, vertical position, and lack of
 // sentence-ending punctuation in the last segment.
-func isSameSentence(last, current Text) bool {
+func IsSameSentence(last, current Text) bool {
 	return last.Font == current.Font &&
 		math.Abs(last.FontSize-current.FontSize) < 0.1 &&
 		math.Abs(last.Y-current.Y) < 5 &&
-		!strings.ContainsAny(last.S, ".!?") &&
 		last.S != ""
 }