Section:

Search PDF for Text / String - TextSearch - Go Sample Code

Sample code for using Apryse SDK to search text on PDF pages using regular expressions; provided in Python, C++, C#, Java, Node.js (JavaScript), PHP, Ruby, Go and VB. The TextSearch utility class builds on functionality available in TextExtractor Sample to simplify most common search operations. Learn more about our Server SDK and PDF Indexed Search Library.

1//---------------------------------------------------------------------------------------
2// Copyright (c) 2001-2021 by PDFTron Systems Inc. All Rights Reserved.
3// Consult LICENSE.txt regarding license information.
4//---------------------------------------------------------------------------------------
5
6package main
7import (
8	"fmt"
9	"strconv"
10	. "math"
11	. "pdftron"
12)
13
14import  "pdftron/Samples/LicenseKey/GO"
15
16// This sample illustrates the basic text search capabilities of PDFNet.
17
18// Relative path to the folder containing the test files.
19var inputPath = "../../TestFiles/"
20var outputPath = "../../TestFiles/Output/"
21
22func main(){
23    // Initialize PDFNet
24    PDFNetInitialize(PDFTronLicense.Key)
25    doc := NewPDFDoc(inputPath + "credit card numbers.pdf")
26    doc.InitSecurityHandler()
27    
28    txtSearch := NewTextSearch()
29    mode := TextSearchE_whole_word | TextSearchE_page_stop
30    
31    pattern := "joHn sMiTh"
32    
33    // call Begin() method to initialize the text search.
34    txtSearch.Begin(doc, pattern, uint(mode))
35
36    step := 0
37    
38    // call Run() method iteratively to find all matching instances.
39    for true{
40        searchResult := txtSearch.Run()
41        if searchResult.IsFound(){
42            if step == 0{
43                // step 0: found "John Smith"
44                // note that, here, 'ambient_string' and 'hlts' are not written to, 
45                // as 'e_ambient_string' and 'e_highlight' are not set.
46                
47                fmt.Println(searchResult.GetMatch() + "'s credit card number is: ")
48                // now switch to using regular expressions to find John's credit card number
49                mode := PdftronPDFTextSearchTextSearchModes(txtSearch.GetMode())
50                mode = mode | TextSearchE_reg_expression | TextSearchE_highlight
51                txtSearch.SetMode(uint(mode))
52                pattern := "\\d{4}-\\d{4}-\\d{4}-\\d{4}"     //or "(\\d{4}-){3}\\d{4}"
53                txtSearch.SetPattern(pattern)
54                step = step + 1
55            }else if step == 1{
56                // step 1: found John's credit card number
57                fmt.Println("  " + searchResult.GetMatch())
58                
59                // note that, here, 'hlts' is written to, as 'e_highligh' has been set.
60                // output the highlight info of the credit card number
61                hlts := searchResult.GetHighlights()
62                hlts.Begin(doc)
63                for hlts.HasNext(){
64                    fmt.Println("The current highlight is from page: " + strconv.Itoa(hlts.GetCurrentPageNumber()))
65                    hlts.Next()
66                }
67                // see if there is an AMEX card number
68                pattern := "\\d{4}-\\d{6}-\\d{5}"
69                txtSearch.SetPattern(pattern)
70                
71                step = step + 1
72            }else if step == 2{
73                // found an AMEX card number
74                fmt.Println("\nThere is an AMEX card number:\n  " + searchResult.GetMatch())
75                
76                // change mode to find the owner of the credit card; supposedly, the owner's
77                // name proceeds the number
78                mode := PdftronPDFTextSearchTextSearchModes(txtSearch.GetMode())
79                mode = mode | TextSearchE_search_up
80                txtSearch.SetMode(uint(mode))
81                pattern := "[A-z]++ [A-z]++"
82                txtSearch.SetPattern(pattern)
83                step = step + 1
84            }else if step == 3{
85                // found the owner's name of the AMEX card
86                fmt.Println("Is the owner's name:\n  " + searchResult.GetMatch() + "?")
87                
88                // add a link annotation based on the location of the found instance
89                hlts := searchResult.GetHighlights()
90                hlts.Begin(doc)
91                
92                for hlts.HasNext(){
93                    curPage := doc.GetPage(uint(hlts.GetCurrentPageNumber()))
94                    quadsInfo := hlts.GetCurrentQuads()
95                    
96                    i := 0
97                    for i < int(quadsInfo.Size()){
98                        q := quadsInfo.Get(i)
99                        // assume each quad is an axis-aligned rectangle 
100                        x1 := Min(Min(Min(q.GetP1().GetX(), q.GetP2().GetX()), q.GetP3().GetX()), q.GetP4().GetX())
101                        x2 := Max(Max(Max(q.GetP1().GetX(), q.GetP2().GetX()), q.GetP3().GetX()), q.GetP4().GetX())
102                        y1 := Min(Min(Min(q.GetP1().GetY(), q.GetP2().GetY()), q.GetP3().GetY()), q.GetP4().GetY())
103                        y2 := Max(Max(Max(q.GetP1().GetY(), q.GetP2().GetY()), q.GetP3().GetY()), q.GetP4().GetY())
104                        hyperLink := LinkCreate(doc.GetSDFDoc(), NewRect(x1, y1, x2, y2), ActionCreateURI(doc.GetSDFDoc(), "http://www.pdftron.com"))
105                        curPage.AnnotPushBack(hyperLink)
106                        i = i + 1
107					}
108                    hlts.Next()
109				}
110                doc.Save(outputPath + "credit card numbers_linked.pdf", uint(SDFDocE_linearized))
111                break
112			}
113        }else if searchResult.IsPageEnd(){
114            //you can update your UI here, if needed
115        }else{
116            break
117		}
118    }    
119    doc.Close()
120    PDFNetTerminate()
121}

Did you find this helpful?

Trial setup questions?

Ask experts on Discord

Need other help?

Contact Support

Pricing or product questions?

Contact Sales