mirror of
https://github.com/Stirling-Tools/Stirling-PDF.git
synced 2025-08-25 05:39:25 +00:00
refactor(tests): move & expand TextFinder/RedactController tests; fix TextFinder empty search-term handling; update token filtering API (#4264)
# Description of Changes - **What was changed** - Relocated and refactored unit tests: - `TextFinderTest` and `RedactControllerTest` moved under `app/core/src/test/...` to align with module structure. - Expanded test coverage: whole-word vs. partial matches, complex regexes (emails, SSNs, IPs, currency), international/accented characters, multi-page documents, malformed PDFs, operator preservation, color decoding, and performance assertions. - **API adjustments in redaction flow**: - `createTokensWithoutTargetText(...)` now accepts the `PDDocument` alongside `PDPage` to properly manage resources/streams. - Introduced/used `createPlaceholderWithFont(...)` to maintain text width with explicit font context. - **Bug fix in `TextFinder`**: - Early-return when the (trimmed) search term is empty to prevent unnecessary processing and avoid false positives/errors. - Minor cleanup (removed redundant `super()` call) and improved guard logic around regex/whole-word wrapping. - **Why the change was made** - Improve reliability and determinism of PDF redaction and text finding by exercising real-world patterns and edge cases. - Ensure structural PDF operators (graphics/positioning) are preserved during token filtering. - Prevent crashes or misleading matches when users provide empty/whitespace-only search terms. - Align tests with the current project layout and increase maintainability. --- ## Checklist ### General - [x] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [x] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md) (if applicable) - [x] I have performed a self-review of my own code - [x] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing) for more details.
This commit is contained in:
Ludy
GitHub
parent
2baa258e11
commit
9779c75df4
@ -27,7 +27,6 @@ public class TextFinder extends PDFTextStripper {
|
||||
|
||||
public TextFinder(String searchTerm, boolean useRegex, boolean wholeWordSearch)
|
||||
throws IOException {
|
||||
super();
|
||||
this.searchTerm = searchTerm;
|
||||
this.useRegex = useRegex;
|
||||
this.wholeWordSearch = wholeWordSearch;
|
||||
@ -68,11 +67,15 @@ public class TextFinder extends PDFTextStripper {
|
||||
}
|
||||
|
||||
String processedSearchTerm = this.searchTerm.trim();
|
||||
if (processedSearchTerm.isEmpty()) {
|
||||
super.endPage(page);
|
||||
return;
|
||||
}
|
||||
String regex = this.useRegex ? processedSearchTerm : "\\Q" + processedSearchTerm + "\\E";
|
||||
if (this.wholeWordSearch) {
|
||||
if (processedSearchTerm.length() == 1
|
||||
&& Character.isDigit(processedSearchTerm.charAt(0))) {
|
||||
regex = "(?<![\\w])" + regex + "(?![\\w])";
|
||||
regex = "(?<![\\w])(?<!\\d[\\.,])" + regex + "(?![\\w])(?![\\.,]\\d)";
|
||||
} else if (processedSearchTerm.length() == 1) {
|
||||
regex = "(?<![\\w])" + regex + "(?![\\w])";
|
||||
} else {
|
||||
|
||||
@ -57,11 +57,9 @@ class RedactControllerTest {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(RedactControllerTest.class);
|
||||
|
||||
@Mock
|
||||
private CustomPDFDocumentFactory pdfDocumentFactory;
|
||||
@Mock private CustomPDFDocumentFactory pdfDocumentFactory;
|
||||
|
||||
@InjectMocks
|
||||
private RedactController redactController;
|
||||
@InjectMocks private RedactController redactController;
|
||||
|
||||
private MockMultipartFile mockPdfFile;
|
||||
private PDDocument mockDocument;
|
||||
@ -72,9 +70,15 @@ class RedactControllerTest {
|
||||
private PDPage realPage;
|
||||
|
||||
// Helpers
|
||||
private void testAutoRedaction(String searchText, boolean useRegex, boolean wholeWordSearch,
|
||||
String redactColor, float padding, boolean convertToImage,
|
||||
boolean expectSuccess) throws Exception {
|
||||
private void testAutoRedaction(
|
||||
String searchText,
|
||||
boolean useRegex,
|
||||
boolean wholeWordSearch,
|
||||
String redactColor,
|
||||
float padding,
|
||||
boolean convertToImage,
|
||||
boolean expectSuccess)
|
||||
throws Exception {
|
||||
RedactPdfRequest request = createRedactPdfRequest();
|
||||
request.setListOfText(searchText);
|
||||
request.setUseRegex(useRegex);
|
||||
@ -103,7 +107,8 @@ class RedactControllerTest {
|
||||
}
|
||||
}
|
||||
|
||||
private void testManualRedaction(List<RedactionArea> redactionAreas, boolean convertToImage) throws Exception {
|
||||
private void testManualRedaction(List<RedactionArea> redactionAreas, boolean convertToImage)
|
||||
throws Exception {
|
||||
ManualRedactPdfRequest request = createManualRedactPdfRequest();
|
||||
request.setRedactions(redactionAreas);
|
||||
request.setConvertPDFToImage(convertToImage);
|
||||
@ -123,18 +128,16 @@ class RedactControllerTest {
|
||||
|
||||
@BeforeEach
|
||||
void setUp() throws IOException {
|
||||
mockPdfFile = new MockMultipartFile(
|
||||
"fileInput",
|
||||
"test.pdf",
|
||||
"application/pdf",
|
||||
createSimplePdfContent()
|
||||
);
|
||||
mockPdfFile =
|
||||
new MockMultipartFile(
|
||||
"fileInput", "test.pdf", "application/pdf", createSimplePdfContent());
|
||||
|
||||
// Mock PDF document and related objects
|
||||
mockDocument = mock(PDDocument.class);
|
||||
mockPages = mock(PDPageTree.class);
|
||||
mockPage = mock(PDPage.class);
|
||||
org.apache.pdfbox.pdmodel.PDDocumentCatalog mockCatalog = mock(org.apache.pdfbox.pdmodel.PDDocumentCatalog.class);
|
||||
org.apache.pdfbox.pdmodel.PDDocumentCatalog mockCatalog =
|
||||
mock(org.apache.pdfbox.pdmodel.PDDocumentCatalog.class);
|
||||
|
||||
// Setup document structure properly
|
||||
when(pdfDocumentFactory.load(any(MockMultipartFile.class))).thenReturn(mockDocument);
|
||||
@ -153,12 +156,14 @@ class RedactControllerTest {
|
||||
when(mockPage.getMediaBox()).thenReturn(pageRect);
|
||||
when(mockPage.getBBox()).thenReturn(pageRect);
|
||||
|
||||
InputStream mockInputStream = new ByteArrayInputStream("BT /F1 12 Tf 100 200 Td (test content) Tj ET".getBytes());
|
||||
InputStream mockInputStream =
|
||||
new ByteArrayInputStream("BT /F1 12 Tf 100 200 Td (test content) Tj ET".getBytes());
|
||||
when(mockPage.getContents()).thenReturn(mockInputStream);
|
||||
|
||||
when(mockPage.hasContents()).thenReturn(true);
|
||||
|
||||
org.apache.pdfbox.cos.COSDocument mockCOSDocument = mock(org.apache.pdfbox.cos.COSDocument.class);
|
||||
org.apache.pdfbox.cos.COSDocument mockCOSDocument =
|
||||
mock(org.apache.pdfbox.cos.COSDocument.class);
|
||||
org.apache.pdfbox.cos.COSStream mockCOSStream = mock(org.apache.pdfbox.cos.COSStream.class);
|
||||
when(mockDocument.getDocument()).thenReturn(mockCOSDocument);
|
||||
when(mockCOSDocument.createCOSStream()).thenReturn(mockCOSStream);
|
||||
@ -167,11 +172,14 @@ class RedactControllerTest {
|
||||
when(mockCOSStream.createOutputStream()).thenReturn(mockOutputStream);
|
||||
when(mockCOSStream.createOutputStream(any())).thenReturn(mockOutputStream);
|
||||
|
||||
doAnswer(invocation -> {
|
||||
ByteArrayOutputStream baos = invocation.getArgument(0);
|
||||
baos.write("Mock PDF Content".getBytes());
|
||||
return null;
|
||||
}).when(mockDocument).save(any(ByteArrayOutputStream.class));
|
||||
doAnswer(
|
||||
invocation -> {
|
||||
ByteArrayOutputStream baos = invocation.getArgument(0);
|
||||
baos.write("Mock PDF Content".getBytes());
|
||||
return null;
|
||||
})
|
||||
.when(mockDocument)
|
||||
.save(any(ByteArrayOutputStream.class));
|
||||
doNothing().when(mockDocument).close();
|
||||
|
||||
// Initialize a real document for unit tests
|
||||
@ -185,7 +193,8 @@ class RedactControllerTest {
|
||||
|
||||
// Set up basic page resources
|
||||
PDResources resources = new PDResources();
|
||||
resources.put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
resources.put(
|
||||
COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.setResources(resources);
|
||||
}
|
||||
|
||||
@ -222,7 +231,14 @@ class RedactControllerTest {
|
||||
@Test
|
||||
@DisplayName("Should redact multiple search terms")
|
||||
void redactMultipleSearchTerms() throws Exception {
|
||||
testAutoRedaction("confidential\nsecret\nprivate\nclassified", false, true, "#FF0000", 2.0f, false, true);
|
||||
testAutoRedaction(
|
||||
"confidential\nsecret\nprivate\nclassified",
|
||||
false,
|
||||
true,
|
||||
"#FF0000",
|
||||
2.0f,
|
||||
false,
|
||||
true);
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -250,8 +266,12 @@ class RedactControllerTest {
|
||||
when(page.getBBox()).thenReturn(pageRect);
|
||||
when(page.hasContents()).thenReturn(true);
|
||||
|
||||
InputStream mockInputStream = new ByteArrayInputStream(
|
||||
("BT /F1 12 Tf 100 200 Td (page " + i + " content with confidential info) Tj ET").getBytes());
|
||||
InputStream mockInputStream =
|
||||
new ByteArrayInputStream(
|
||||
("BT /F1 12 Tf 100 200 Td (page "
|
||||
+ i
|
||||
+ " content with confidential info) Tj ET")
|
||||
.getBytes());
|
||||
when(page.getContents()).thenReturn(mockInputStream);
|
||||
|
||||
pageList.add(page);
|
||||
@ -285,7 +305,8 @@ class RedactControllerTest {
|
||||
|
||||
when(mockPages.get(0)).thenReturn(mockPage);
|
||||
|
||||
org.apache.pdfbox.pdmodel.PDDocumentInformation mockInfo = mock(org.apache.pdfbox.pdmodel.PDDocumentInformation.class);
|
||||
org.apache.pdfbox.pdmodel.PDDocumentInformation mockInfo =
|
||||
mock(org.apache.pdfbox.pdmodel.PDDocumentInformation.class);
|
||||
when(mockDocument.getDocumentInformation()).thenReturn(mockInfo);
|
||||
|
||||
ResponseEntity<byte[]> response = redactController.redactPdf(request);
|
||||
@ -311,23 +332,27 @@ class RedactControllerTest {
|
||||
@Test
|
||||
@DisplayName("Should handle email pattern redaction")
|
||||
void handleEmailPatternRedaction() throws Exception {
|
||||
testAutoRedaction("[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}", true, false, "#0000FF", 1.5f, false, true);
|
||||
testAutoRedaction(
|
||||
"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}",
|
||||
true, false, "#0000FF", 1.5f, false, true);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should handle phone number patterns")
|
||||
void handlePhoneNumberPatterns() throws Exception {
|
||||
testAutoRedaction("\\(\\d{3}\\)\\s*\\d{3}-\\d{4}", true, false, "#FF0000", 1.0f, false, true);
|
||||
testAutoRedaction(
|
||||
"\\(\\d{3}\\)\\s*\\d{3}-\\d{4}", true, false, "#FF0000", 1.0f, false, true);
|
||||
}
|
||||
|
||||
@ParameterizedTest
|
||||
@ValueSource(strings = {
|
||||
"\\d{3}-\\d{2}-\\d{4}", // SSN pattern
|
||||
"\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}", // Credit card pattern
|
||||
"\\b[A-Z]{2,}\\b", // Uppercase words
|
||||
"\\$\\d+\\.\\d{2}", // Currency pattern
|
||||
"\\b\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\b" // IP address pattern
|
||||
})
|
||||
@ValueSource(
|
||||
strings = {
|
||||
"\\d{3}-\\d{2}-\\d{4}", // SSN pattern
|
||||
"\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}[\\s-]?\\d{4}", // Credit card pattern
|
||||
"\\b[A-Z]{2,}\\b", // Uppercase words
|
||||
"\\$\\d+\\.\\d{2}", // Currency pattern
|
||||
"\\b\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\b" // IP address pattern
|
||||
})
|
||||
@DisplayName("Should handle various regex patterns")
|
||||
void handleVariousRegexPatterns(String regexPattern) throws Exception {
|
||||
testAutoRedaction(regexPattern, true, false, "#000000", 1.0f, false, true);
|
||||
@ -519,8 +544,10 @@ class RedactControllerTest {
|
||||
when(page.getBBox()).thenReturn(pageRect);
|
||||
when(page.hasContents()).thenReturn(true);
|
||||
|
||||
InputStream mockInputStream = new ByteArrayInputStream(
|
||||
("BT /F1 12 Tf 100 200 Td (page " + i + " content) Tj ET").getBytes());
|
||||
InputStream mockInputStream =
|
||||
new ByteArrayInputStream(
|
||||
("BT /F1 12 Tf 100 200 Td (page " + i + " content) Tj ET")
|
||||
.getBytes());
|
||||
when(page.getContents()).thenReturn(mockInputStream);
|
||||
|
||||
pageList.add(page);
|
||||
@ -588,36 +615,38 @@ class RedactControllerTest {
|
||||
request.setFileInput(null);
|
||||
request.setListOfText("test");
|
||||
|
||||
assertDoesNotThrow(() -> {
|
||||
try {
|
||||
redactController.redactPdf(request);
|
||||
} catch (Exception e) {
|
||||
assertNotNull(e);
|
||||
}
|
||||
});
|
||||
assertDoesNotThrow(
|
||||
() -> {
|
||||
try {
|
||||
redactController.redactPdf(request);
|
||||
} catch (Exception e) {
|
||||
assertNotNull(e);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should handle malformed PDF gracefully")
|
||||
void handleMalformedPdfGracefully() throws Exception {
|
||||
MockMultipartFile malformedFile = new MockMultipartFile(
|
||||
"fileInput",
|
||||
"malformed.pdf",
|
||||
"application/pdf",
|
||||
"Not a real PDF content".getBytes()
|
||||
);
|
||||
MockMultipartFile malformedFile =
|
||||
new MockMultipartFile(
|
||||
"fileInput",
|
||||
"malformed.pdf",
|
||||
"application/pdf",
|
||||
"Not a real PDF content".getBytes());
|
||||
|
||||
RedactPdfRequest request = new RedactPdfRequest();
|
||||
request.setFileInput(malformedFile);
|
||||
request.setListOfText("test");
|
||||
|
||||
assertDoesNotThrow(() -> {
|
||||
try {
|
||||
redactController.redactPdf(request);
|
||||
} catch (Exception e) {
|
||||
assertNotNull(e);
|
||||
}
|
||||
});
|
||||
assertDoesNotThrow(
|
||||
() -> {
|
||||
try {
|
||||
redactController.redactPdf(request);
|
||||
} catch (Exception e) {
|
||||
assertNotNull(e);
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -723,14 +752,24 @@ class RedactControllerTest {
|
||||
}
|
||||
|
||||
@ParameterizedTest
|
||||
@ValueSource(strings = {"#FF0000", "#00FF00", "#0000FF", "#FFFFFF", "#000000", "FF0000", "00FF00", "0000FF"})
|
||||
@ValueSource(
|
||||
strings = {
|
||||
"#FF0000", "#00FF00", "#0000FF", "#FFFFFF", "#000000", "FF0000", "00FF00",
|
||||
"0000FF"
|
||||
})
|
||||
@DisplayName("Should handle various valid color formats")
|
||||
void handleVariousValidColorFormats(String colorInput) throws Exception {
|
||||
Color result = redactController.decodeOrDefault(colorInput);
|
||||
assertNotNull(result);
|
||||
assertTrue(result.getRed() >= 0 && result.getRed() <= 255, "Red component should be in valid range");
|
||||
assertTrue(result.getGreen() >= 0 && result.getGreen() <= 255, "Green component should be in valid range");
|
||||
assertTrue(result.getBlue() >= 0 && result.getBlue() <= 255, "Blue component should be in valid range");
|
||||
assertTrue(
|
||||
result.getRed() >= 0 && result.getRed() <= 255,
|
||||
"Red component should be in valid range");
|
||||
assertTrue(
|
||||
result.getGreen() >= 0 && result.getGreen() <= 255,
|
||||
"Green component should be in valid range");
|
||||
assertTrue(
|
||||
result.getBlue() >= 0 && result.getBlue() <= 255,
|
||||
"Blue component should be in valid range");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -755,16 +794,18 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("confidential");
|
||||
|
||||
List<Object> tokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> tokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
assertNotNull(tokens);
|
||||
assertFalse(tokens.isEmpty());
|
||||
|
||||
String reconstructedText = extractTextFromTokens(tokens);
|
||||
assertFalse(reconstructedText.contains("confidential"),
|
||||
"Target text should be replaced with placeholder");
|
||||
assertTrue(reconstructedText.contains("document"),
|
||||
"Non-target text should remain");
|
||||
assertFalse(
|
||||
reconstructedText.contains("confidential"),
|
||||
"Target text should be replaced with placeholder");
|
||||
assertTrue(reconstructedText.contains("document"), "Non-target text should remain");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -774,7 +815,9 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("secret");
|
||||
|
||||
List<Object> tokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> tokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
assertNotNull(tokens);
|
||||
|
||||
@ -785,7 +828,9 @@ class RedactControllerTest {
|
||||
if (array.getObject(i) instanceof COSString cosString) {
|
||||
String text = cosString.getString();
|
||||
if (text.contains("secret")) {
|
||||
fail("Target text 'secret' should have been redacted from TJ array");
|
||||
fail(
|
||||
"Target text 'secret' should have been redacted from TJ"
|
||||
+ " array");
|
||||
}
|
||||
foundModifiedTJArray = true;
|
||||
}
|
||||
@ -803,21 +848,33 @@ class RedactControllerTest {
|
||||
Set<String> targetWords = Set.of("redact");
|
||||
|
||||
List<Object> originalTokens = getOriginalTokens();
|
||||
List<Object> filteredTokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> filteredTokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
long originalNonTextCount = originalTokens.stream()
|
||||
.filter(token -> token instanceof Operator op && !redactController.isTextShowingOperator(op.getName()))
|
||||
.count();
|
||||
long originalNonTextCount =
|
||||
originalTokens.stream()
|
||||
.filter(
|
||||
token ->
|
||||
token instanceof Operator op
|
||||
&& !redactController.isTextShowingOperator(
|
||||
op.getName()))
|
||||
.count();
|
||||
|
||||
long filteredNonTextCount = filteredTokens.stream()
|
||||
.filter(token -> token instanceof Operator op && !redactController.isTextShowingOperator(op.getName()))
|
||||
.count();
|
||||
long filteredNonTextCount =
|
||||
filteredTokens.stream()
|
||||
.filter(
|
||||
token ->
|
||||
token instanceof Operator op
|
||||
&& !redactController.isTextShowingOperator(
|
||||
op.getName()))
|
||||
.count();
|
||||
|
||||
assertTrue(filteredNonTextCount > 0,
|
||||
"Non-text operators should be preserved");
|
||||
assertTrue(filteredNonTextCount > 0, "Non-text operators should be preserved");
|
||||
|
||||
assertTrue(filteredNonTextCount >= originalNonTextCount / 2,
|
||||
"A reasonable number of non-text operators should be preserved");
|
||||
assertTrue(
|
||||
filteredNonTextCount >= originalNonTextCount / 2,
|
||||
"A reasonable number of non-text operators should be preserved");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -827,7 +884,9 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("\\d{3}-\\d{2}-\\d{4}"); // SSN pattern
|
||||
|
||||
List<Object> tokens = redactController.createTokensWithoutTargetText(realPage, targetWords, true, false);
|
||||
List<Object> tokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, true, false);
|
||||
|
||||
String reconstructedText = extractTextFromTokens(tokens);
|
||||
assertFalse(reconstructedText.contains("111-22-3333"), "SSN should be redacted");
|
||||
@ -841,7 +900,9 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("test");
|
||||
|
||||
List<Object> tokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, true);
|
||||
List<Object> tokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, true);
|
||||
|
||||
String reconstructedText = extractTextFromTokens(tokens);
|
||||
assertTrue(reconstructedText.contains("testing"), "Partial matches should remain");
|
||||
@ -856,11 +917,14 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("sensitive");
|
||||
|
||||
List<Object> tokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> tokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
String reconstructedText = extractTextFromTokens(tokens);
|
||||
assertFalse(reconstructedText.contains("sensitive"),
|
||||
"Text should be redacted regardless of operator type");
|
||||
assertFalse(
|
||||
reconstructedText.contains("sensitive"),
|
||||
"Text should be redacted regardless of operator type");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -884,7 +948,10 @@ class RedactControllerTest {
|
||||
void shouldHandleEmptyTokenList() throws Exception {
|
||||
List<Object> emptyTokens = Collections.emptyList();
|
||||
|
||||
assertDoesNotThrow(() -> redactController.writeFilteredContentStream(realDocument, realPage, emptyTokens));
|
||||
assertDoesNotThrow(
|
||||
() ->
|
||||
redactController.writeFilteredContentStream(
|
||||
realDocument, realPage, emptyTokens));
|
||||
|
||||
assertNotNull(realPage.getContents(), "Page should still have content stream");
|
||||
}
|
||||
@ -906,20 +973,27 @@ class RedactControllerTest {
|
||||
@DisplayName("Placeholder creation should maintain text width")
|
||||
void shouldCreateWidthMatchingPlaceholder() throws Exception {
|
||||
String originalText = "confidential";
|
||||
String placeholder = redactController.createPlaceholder(originalText);
|
||||
String placeholder =
|
||||
redactController.createPlaceholderWithFont(
|
||||
originalText, new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
assertEquals(originalText.length(), placeholder.length(),
|
||||
"Placeholder should maintain character count for width preservation");
|
||||
assertEquals(
|
||||
originalText.length(),
|
||||
placeholder.length(),
|
||||
"Placeholder should maintain character count for width preservation");
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Placeholder should handle special characters")
|
||||
void shouldHandleSpecialCharactersInPlaceholder() throws Exception {
|
||||
String originalText = "café naïve";
|
||||
String placeholder = redactController.createPlaceholder(originalText);
|
||||
String placeholder =
|
||||
redactController.createPlaceholderWithFont(
|
||||
originalText, new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
assertEquals(originalText.length(), placeholder.length());
|
||||
assertFalse(placeholder.contains("café"), "Placeholder should not contain original text");
|
||||
assertFalse(
|
||||
placeholder.contains("café"), "Placeholder should not contain original text");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -929,7 +1003,9 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("secret");
|
||||
|
||||
List<Object> filteredTokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> filteredTokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
redactController.writeFilteredContentStream(realDocument, realPage, filteredTokens);
|
||||
assertNotNull(realPage.getContents());
|
||||
@ -946,15 +1022,21 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("confidential");
|
||||
|
||||
List<Object> filteredTokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> filteredTokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
long filteredPositioning = filteredTokens.stream()
|
||||
.filter(token -> token instanceof Operator op &&
|
||||
(op.getName().equals("Td") || op.getName().equals("TD") || op.getName().equals("Tm")))
|
||||
.count();
|
||||
long filteredPositioning =
|
||||
filteredTokens.stream()
|
||||
.filter(
|
||||
token ->
|
||||
token instanceof Operator op
|
||||
&& ("Td".equals(op.getName())
|
||||
|| "TD".equals(op.getName())
|
||||
|| "Tm".equals(op.getName())))
|
||||
.count();
|
||||
|
||||
assertTrue(filteredPositioning > 0,
|
||||
"Positioning operators should be preserved");
|
||||
assertTrue(filteredPositioning > 0, "Positioning operators should be preserved");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -966,16 +1048,21 @@ class RedactControllerTest {
|
||||
}
|
||||
realDocument.addPage(realPage);
|
||||
realPage.setResources(new PDResources());
|
||||
realPage.getResources().put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.getResources()
|
||||
.put(
|
||||
COSName.getPDFName("F1"),
|
||||
new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, realPage)) {
|
||||
try (PDPageContentStream contentStream =
|
||||
new PDPageContentStream(realDocument, realPage)) {
|
||||
contentStream.setLineWidth(2);
|
||||
contentStream.moveTo(100, 100);
|
||||
contentStream.lineTo(200, 200);
|
||||
contentStream.stroke();
|
||||
|
||||
contentStream.beginText();
|
||||
contentStream.setFont(realPage.getResources().getFont(COSName.getPDFName("F1")), 12);
|
||||
contentStream.setFont(
|
||||
realPage.getResources().getFont(COSName.getPDFName("F1")), 12);
|
||||
contentStream.newLineAtOffset(50, 750);
|
||||
contentStream.showText("This is a complex document with ");
|
||||
contentStream.setTextRise(5);
|
||||
@ -990,19 +1077,27 @@ class RedactControllerTest {
|
||||
|
||||
Set<String> targetWords = Set.of("confidential");
|
||||
|
||||
List<Object> tokens = redactController.createTokensWithoutTargetText(realPage, targetWords, false, false);
|
||||
List<Object> tokens =
|
||||
redactController.createTokensWithoutTargetText(
|
||||
realDocument, realPage, targetWords, false, false);
|
||||
|
||||
assertNotNull(tokens);
|
||||
assertFalse(tokens.isEmpty());
|
||||
|
||||
String reconstructedText = extractTextFromTokens(tokens);
|
||||
assertFalse(reconstructedText.contains("confidential"), "Target text should be redacted");
|
||||
assertFalse(
|
||||
reconstructedText.contains("confidential"), "Target text should be redacted");
|
||||
|
||||
boolean hasGraphicsOperators = tokens.stream()
|
||||
.anyMatch(token -> token instanceof Operator op &&
|
||||
(op.getName().equals("re") || op.getName().equals("f") ||
|
||||
op.getName().equals("m") || op.getName().equals("l") ||
|
||||
op.getName().equals("S")));
|
||||
boolean hasGraphicsOperators =
|
||||
tokens.stream()
|
||||
.anyMatch(
|
||||
token ->
|
||||
token instanceof Operator op
|
||||
&& ("re".equals(op.getName())
|
||||
|| "f".equals(op.getName())
|
||||
|| "m".equals(op.getName())
|
||||
|| "l".equals(op.getName())
|
||||
|| "S".equals(op.getName())));
|
||||
|
||||
assertTrue(hasGraphicsOperators, "Graphics operators should be preserved");
|
||||
}
|
||||
@ -1019,10 +1114,12 @@ class RedactControllerTest {
|
||||
|
||||
// Create resources
|
||||
PDResources resources = new PDResources();
|
||||
resources.put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
resources.put(
|
||||
COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.setResources(resources);
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, realPage)) {
|
||||
try (PDPageContentStream contentStream =
|
||||
new PDPageContentStream(realDocument, realPage)) {
|
||||
contentStream.beginText();
|
||||
contentStream.setFont(new PDType1Font(Standard14Fonts.FontName.HELVETICA), 12);
|
||||
contentStream.newLineAtOffset(50, 750);
|
||||
@ -1180,7 +1277,8 @@ class RedactControllerTest {
|
||||
}
|
||||
realDocument.addPage(realPage);
|
||||
realPage.setResources(new PDResources());
|
||||
realPage.getResources().put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.getResources()
|
||||
.put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, realPage)) {
|
||||
contentStream.beginText();
|
||||
@ -1198,7 +1296,8 @@ class RedactControllerTest {
|
||||
}
|
||||
realDocument.addPage(realPage);
|
||||
realPage.setResources(new PDResources());
|
||||
realPage.getResources().put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.getResources()
|
||||
.put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, realPage)) {
|
||||
contentStream.beginText();
|
||||
@ -1221,7 +1320,8 @@ class RedactControllerTest {
|
||||
}
|
||||
realDocument.addPage(realPage);
|
||||
realPage.setResources(new PDResources());
|
||||
realPage.getResources().put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.getResources()
|
||||
.put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, realPage)) {
|
||||
contentStream.setLineWidth(2);
|
||||
@ -1248,7 +1348,8 @@ class RedactControllerTest {
|
||||
}
|
||||
realDocument.addPage(realPage);
|
||||
realPage.setResources(new PDResources());
|
||||
realPage.getResources().put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
realPage.getResources()
|
||||
.put(COSName.getPDFName("F1"), new PDType1Font(Standard14Fonts.FontName.HELVETICA));
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, realPage)) {
|
||||
contentStream.beginText();
|
||||
@ -1266,28 +1367,29 @@ class RedactControllerTest {
|
||||
// Helper for token creation
|
||||
private List<Object> createSampleTokenList() {
|
||||
return List.of(
|
||||
Operator.getOperator("BT"),
|
||||
COSName.getPDFName("F1"),
|
||||
new COSFloat(12),
|
||||
Operator.getOperator("Tf"),
|
||||
new COSString("Sample text"),
|
||||
Operator.getOperator("Tj"),
|
||||
Operator.getOperator("ET")
|
||||
);
|
||||
Operator.getOperator("BT"),
|
||||
COSName.getPDFName("F1"),
|
||||
new COSFloat(12),
|
||||
Operator.getOperator("Tf"),
|
||||
new COSString("Sample text"),
|
||||
Operator.getOperator("Tj"),
|
||||
Operator.getOperator("ET"));
|
||||
}
|
||||
|
||||
private List<Object> getOriginalTokens() throws Exception {
|
||||
// Create a new page to avoid side effects from other tests
|
||||
PDPage pageForTokenExtraction = new PDPage(PDRectangle.A4);
|
||||
pageForTokenExtraction.setResources(realPage.getResources());
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(realDocument, pageForTokenExtraction)) {
|
||||
contentStream.beginText();
|
||||
contentStream.setFont(realPage.getResources().getFont(COSName.getPDFName("F1")), 12);
|
||||
contentStream.newLineAtOffset(50, 750);
|
||||
contentStream.showText("Original content");
|
||||
contentStream.endText();
|
||||
try (PDPageContentStream contentStream =
|
||||
new PDPageContentStream(realDocument, pageForTokenExtraction)) {
|
||||
contentStream.beginText();
|
||||
contentStream.setFont(realPage.getResources().getFont(COSName.getPDFName("F1")), 12);
|
||||
contentStream.newLineAtOffset(50, 750);
|
||||
contentStream.showText("Original content");
|
||||
contentStream.endText();
|
||||
}
|
||||
return redactController.createTokensWithoutTargetText(pageForTokenExtraction, Collections.emptySet(), false, false);
|
||||
return redactController.createTokensWithoutTargetText(
|
||||
realDocument, pageForTokenExtraction, Collections.emptySet(), false, false);
|
||||
}
|
||||
|
||||
private String extractTextFromTokens(List<Object> tokens) {
|
||||
@ -1,5 +1,11 @@
|
||||
package stirling.software.SPDF.pdf;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertDoesNotThrow;
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
import static org.junit.jupiter.api.Assertions.assertFalse;
|
||||
import static org.junit.jupiter.api.Assertions.assertNotNull;
|
||||
import static org.junit.jupiter.api.Assertions.assertTrue;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.List;
|
||||
|
||||
@ -10,11 +16,6 @@ import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.font.PDType1Font;
|
||||
import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
|
||||
import org.junit.jupiter.api.AfterEach;
|
||||
import static org.junit.jupiter.api.Assertions.assertDoesNotThrow;
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
import static org.junit.jupiter.api.Assertions.assertFalse;
|
||||
import static org.junit.jupiter.api.Assertions.assertNotNull;
|
||||
import static org.junit.jupiter.api.Assertions.assertTrue;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.DisplayName;
|
||||
import org.junit.jupiter.api.Nested;
|
||||
@ -34,33 +35,44 @@ class TextFinderTest {
|
||||
private PDPage page;
|
||||
|
||||
// Helpers
|
||||
private void testTextFinding(String pageContent, String searchTerm, boolean useRegex, boolean wholeWord,
|
||||
String[] expectedTexts, int expectedCount) throws IOException {
|
||||
private void testTextFinding(
|
||||
String pageContent,
|
||||
String searchTerm,
|
||||
boolean useRegex,
|
||||
boolean wholeWord,
|
||||
String[] expectedTexts,
|
||||
int expectedCount)
|
||||
throws IOException {
|
||||
addTextToPage(pageContent);
|
||||
TextFinder textFinder = new TextFinder(searchTerm, useRegex, wholeWord);
|
||||
|
||||
textFinder.getText(document);
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
|
||||
assertEquals(expectedCount, foundTexts.size(),
|
||||
String.format("Expected %d matches for search term '%s'", expectedCount, searchTerm));
|
||||
assertEquals(
|
||||
expectedCount,
|
||||
foundTexts.size(),
|
||||
String.format(
|
||||
"Expected %d matches for search term '%s'", expectedCount, searchTerm));
|
||||
|
||||
if (expectedTexts != null) {
|
||||
for (String expectedText : expectedTexts) {
|
||||
assertTrue(foundTexts.stream().anyMatch(text -> text.getText().equals(expectedText)),
|
||||
String.format("Expected to find text: '%s'", expectedText));
|
||||
assertTrue(
|
||||
foundTexts.stream().anyMatch(text -> text.getText().equals(expectedText)),
|
||||
String.format("Expected to find text: '%s'", expectedText));
|
||||
}
|
||||
}
|
||||
|
||||
// Verify basic properties of found texts
|
||||
foundTexts.forEach(text -> {
|
||||
assertNotNull(text.getText());
|
||||
assertTrue(text.getX1() >= 0);
|
||||
assertTrue(text.getY1() >= 0);
|
||||
assertTrue(text.getX2() >= text.getX1());
|
||||
assertTrue(text.getY2() >= text.getY1());
|
||||
assertEquals(0, text.getPageIndex()); // Single page test
|
||||
});
|
||||
foundTexts.forEach(
|
||||
text -> {
|
||||
assertNotNull(text.getText());
|
||||
assertTrue(text.getX1() >= 0);
|
||||
assertTrue(text.getY1() >= 0);
|
||||
assertTrue(text.getX2() >= text.getX1());
|
||||
assertTrue(text.getY2() >= text.getY1());
|
||||
assertEquals(0, text.getPageIndex()); // Single page test
|
||||
});
|
||||
}
|
||||
|
||||
@BeforeEach
|
||||
@ -84,25 +96,37 @@ class TextFinderTest {
|
||||
@Test
|
||||
@DisplayName("Should find simple text correctly")
|
||||
void findSimpleText() throws IOException {
|
||||
testTextFinding("This is a confidential document with secret information.",
|
||||
"confidential", false, false,
|
||||
new String[]{"confidential"}, 1);
|
||||
testTextFinding(
|
||||
"This is a confidential document with secret information.",
|
||||
"confidential",
|
||||
false,
|
||||
false,
|
||||
new String[] {"confidential"},
|
||||
1);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should perform case-insensitive search")
|
||||
void performCaseInsensitiveSearch() throws IOException {
|
||||
testTextFinding("This document contains CONFIDENTIAL information.",
|
||||
"confidential", false, false,
|
||||
new String[]{"CONFIDENTIAL"}, 1);
|
||||
testTextFinding(
|
||||
"This document contains CONFIDENTIAL information.",
|
||||
"confidential",
|
||||
false,
|
||||
false,
|
||||
new String[] {"CONFIDENTIAL"},
|
||||
1);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find multiple occurrences of same term")
|
||||
void findMultipleOccurrences() throws IOException {
|
||||
testTextFinding("The secret code is secret123. Keep this secret safe!",
|
||||
"secret", false, false,
|
||||
new String[]{"secret", "secret", "secret"}, 3);
|
||||
testTextFinding(
|
||||
"The secret code is secret123. Keep this secret safe!",
|
||||
"secret",
|
||||
false,
|
||||
false,
|
||||
new String[] {"secret", "secret", "secret"},
|
||||
3);
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -131,33 +155,49 @@ class TextFinderTest {
|
||||
@Test
|
||||
@DisplayName("Should find only whole words when enabled")
|
||||
void findOnlyWholeWords() throws IOException {
|
||||
testTextFinding("This is a test testing document with tested results.",
|
||||
"test", false, true,
|
||||
new String[]{"test"}, 1);
|
||||
testTextFinding(
|
||||
"This is a test testing document with tested results.",
|
||||
"test",
|
||||
false,
|
||||
true,
|
||||
new String[] {"test"},
|
||||
1);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find partial matches when whole word search disabled")
|
||||
void findPartialMatches() throws IOException {
|
||||
testTextFinding("This is a test testing document with tested results.",
|
||||
"test", false, false,
|
||||
new String[]{"test", "test", "test"}, 3);
|
||||
testTextFinding(
|
||||
"This is a test testing document with tested results.",
|
||||
"test",
|
||||
false,
|
||||
false,
|
||||
new String[] {"test", "test", "test"},
|
||||
3);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should handle punctuation boundaries correctly")
|
||||
void handlePunctuationBoundaries() throws IOException {
|
||||
testTextFinding("Hello, world! Testing: test-case (test).",
|
||||
"test", false, true,
|
||||
new String[]{"test"}, 2); // Both standalone "test" and "test" in "test-case"
|
||||
testTextFinding(
|
||||
"Hello, world! Testing: test-case (test).",
|
||||
"test",
|
||||
false,
|
||||
true,
|
||||
new String[] {"test"},
|
||||
2); // Both standalone "test" and "test" in "test-case"
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should handle word boundaries with special characters")
|
||||
void handleSpecialCharacterBoundaries() throws IOException {
|
||||
testTextFinding("Email: test@example.com and test.txt file",
|
||||
"test", false, true,
|
||||
new String[]{"test"}, 2); // Both in email and filename should match
|
||||
testTextFinding(
|
||||
"Email: test@example.com and test.txt file",
|
||||
"test",
|
||||
false,
|
||||
true,
|
||||
new String[] {"test"},
|
||||
2); // Both in email and filename should match
|
||||
}
|
||||
}
|
||||
|
||||
@ -168,46 +208,64 @@ class TextFinderTest {
|
||||
@Test
|
||||
@DisplayName("Should find text matching regex pattern")
|
||||
void findTextMatchingRegex() throws IOException {
|
||||
testTextFinding("Contact John at 123-45-6789 or Jane at 987-65-4321 for details.",
|
||||
"\\d{3}-\\d{2}-\\d{4}", true, false,
|
||||
new String[]{"123-45-6789", "987-65-4321"}, 2);
|
||||
testTextFinding(
|
||||
"Contact John at 123-45-6789 or Jane at 987-65-4321 for details.",
|
||||
"\\d{3}-\\d{2}-\\d{4}",
|
||||
true,
|
||||
false,
|
||||
new String[] {"123-45-6789", "987-65-4321"},
|
||||
2);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find email addresses with regex")
|
||||
void findEmailAddresses() throws IOException {
|
||||
testTextFinding("Email: test@example.com and admin@test.org",
|
||||
"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}", true, false,
|
||||
new String[]{"test@example.com", "admin@test.org"}, 2);
|
||||
testTextFinding(
|
||||
"Email: test@example.com and admin@test.org",
|
||||
"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}",
|
||||
true,
|
||||
false,
|
||||
new String[] {"test@example.com", "admin@test.org"},
|
||||
2);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should combine regex with whole word search")
|
||||
void combineRegexWithWholeWord() throws IOException {
|
||||
testTextFinding("Email: test@example.com and admin@test.org",
|
||||
"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}", true, true,
|
||||
new String[]{"test@example.com", "admin@test.org"}, 2);
|
||||
testTextFinding(
|
||||
"Email: test@example.com and admin@test.org",
|
||||
"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}",
|
||||
true,
|
||||
true,
|
||||
new String[] {"test@example.com", "admin@test.org"},
|
||||
2);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find currency patterns")
|
||||
void findCurrencyPatterns() throws IOException {
|
||||
testTextFinding("Price: $100.50 and €75.25",
|
||||
"\\$\\d+\\.\\d{2}", true, false,
|
||||
new String[]{"$100.50"}, 1);
|
||||
testTextFinding(
|
||||
"Price: $100.50 and €75.25",
|
||||
"\\$\\d+\\.\\d{2}",
|
||||
true,
|
||||
false,
|
||||
new String[] {"$100.50"},
|
||||
1);
|
||||
}
|
||||
|
||||
@ParameterizedTest
|
||||
@ValueSource(strings = {
|
||||
"\\d{4}-\\d{2}-\\d{2}", // Date pattern
|
||||
"\\b[A-Z]{2,}\\b", // Uppercase words
|
||||
"\\w+@\\w+\\.\\w+", // Simple email pattern
|
||||
"\\$\\d+", // Simple currency
|
||||
"\\b\\d{3,4}\\b" // 3-4 digit numbers
|
||||
})
|
||||
@ValueSource(
|
||||
strings = {
|
||||
"\\d{4}-\\d{2}-\\d{2}", // Date pattern
|
||||
"\\b[A-Z]{2,}\\b", // Uppercase words
|
||||
"\\w+@\\w+\\.\\w+", // Simple email pattern
|
||||
"\\$\\d+", // Simple currency
|
||||
"\\b\\d{3,4}\\b" // 3-4 digit numbers
|
||||
})
|
||||
@DisplayName("Should handle various regex patterns")
|
||||
void handleVariousRegexPatterns(String regexPattern) throws IOException {
|
||||
String testContent = "Date: 2023-12-25, Email: test@domain.com, Price: $250, Code: ABC123, Number: 1234";
|
||||
String testContent =
|
||||
"Date: 2023-12-25, Email: test@domain.com, Price: $250, Code: ABC123, Number: 1234";
|
||||
addTextToPage(testContent);
|
||||
|
||||
TextFinder textFinder = new TextFinder(regexPattern, true, false);
|
||||
@ -215,7 +273,9 @@ class TextFinderTest {
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
|
||||
// Each pattern should find at least one match in our test content
|
||||
assertFalse(foundTexts.isEmpty(), String.format("Pattern '%s' should find at least one match", regexPattern));
|
||||
assertFalse(
|
||||
foundTexts.isEmpty(),
|
||||
String.format("Pattern '%s' should find at least one match", regexPattern));
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -230,9 +290,10 @@ class TextFinderTest {
|
||||
assertNotNull(foundTexts);
|
||||
} catch (java.util.regex.PatternSyntaxException e) {
|
||||
assertNotNull(e.getMessage());
|
||||
assertTrue(e.getMessage().contains("Unclosed character class") ||
|
||||
e.getMessage().contains("syntax"),
|
||||
"Exception should indicate regex syntax error");
|
||||
assertTrue(
|
||||
e.getMessage().contains("Unclosed character class")
|
||||
|| e.getMessage().contains("syntax"),
|
||||
"Exception should indicate regex syntax error");
|
||||
} catch (RuntimeException | IOException e) {
|
||||
assertNotNull(e.getMessage());
|
||||
}
|
||||
@ -246,33 +307,38 @@ class TextFinderTest {
|
||||
@Test
|
||||
@DisplayName("Should handle international characters")
|
||||
void handleInternationalCharacters() throws IOException {
|
||||
testTextFinding("Hello café naïve résumé",
|
||||
"café", false, false,
|
||||
new String[]{"café"}, 1);
|
||||
testTextFinding(
|
||||
"Hello café naïve résumé", "café", false, false, new String[] {"café"}, 1);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find text with accented characters")
|
||||
void findAccentedCharacters() throws IOException {
|
||||
testTextFinding("Café, naïve, résumé, piñata",
|
||||
"café", false, false,
|
||||
new String[]{"Café"}, 1); // Case insensitive
|
||||
testTextFinding(
|
||||
"Café, naïve, résumé, piñata",
|
||||
"café",
|
||||
false,
|
||||
false,
|
||||
new String[] {"Café"},
|
||||
1); // Case insensitive
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should handle special symbols")
|
||||
void handleSpecialSymbols() throws IOException {
|
||||
testTextFinding("Symbols: © ® ™ ± × ÷ § ¶",
|
||||
"©", false, false,
|
||||
new String[]{"©"}, 1);
|
||||
testTextFinding("Symbols: © ® ™ ± × ÷ § ¶", "©", false, false, new String[] {"©"}, 1);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find currency symbols")
|
||||
void findCurrencySymbols() throws IOException {
|
||||
testTextFinding("Prices: $100 €75 £50 ¥1000",
|
||||
"[€£¥]", true, false,
|
||||
new String[]{"€", "£", "¥"}, 3);
|
||||
testTextFinding(
|
||||
"Prices: $100 €75 £50 ¥1000",
|
||||
"[€£¥]",
|
||||
true,
|
||||
false,
|
||||
new String[] {"€", "£", "¥"},
|
||||
3);
|
||||
}
|
||||
}
|
||||
|
||||
@ -330,7 +396,7 @@ class TextFinderTest {
|
||||
String longTerm = "a".repeat(1000);
|
||||
String content = "Short text with " + longTerm + " embedded.";
|
||||
|
||||
testTextFinding(content, longTerm, false, false, new String[]{longTerm}, 1);
|
||||
testTextFinding(content, longTerm, false, false, new String[] {longTerm}, 1);
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -350,8 +416,9 @@ class TextFinderTest {
|
||||
long endTime = System.currentTimeMillis();
|
||||
|
||||
assertEquals(10, foundTexts.size());
|
||||
assertTrue(endTime - startTime < 3000,
|
||||
"Multi-page search should complete within 3 seconds");
|
||||
assertTrue(
|
||||
endTime - startTime < 3000,
|
||||
"Multi-page search should complete within 3 seconds");
|
||||
}
|
||||
}
|
||||
|
||||
@ -402,12 +469,13 @@ class TextFinderTest {
|
||||
|
||||
String complexRegex = "(?=.*\\d)(?=.*[a-z])(?=.*[A-Z])[a-zA-Z\\d]{6}";
|
||||
|
||||
assertDoesNotThrow(() -> {
|
||||
TextFinder textFinder = new TextFinder(complexRegex, true, false);
|
||||
textFinder.getText(document);
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
assertNotNull(foundTexts);
|
||||
});
|
||||
assertDoesNotThrow(
|
||||
() -> {
|
||||
TextFinder textFinder = new TextFinder(complexRegex, true, false);
|
||||
textFinder.getText(document);
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
assertNotNull(foundTexts);
|
||||
});
|
||||
}
|
||||
|
||||
@ParameterizedTest
|
||||
@ -464,10 +532,11 @@ class TextFinderTest {
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
|
||||
assertFalse(foundTexts.isEmpty());
|
||||
foundTexts.forEach(text -> {
|
||||
assertNotNull(text.getText());
|
||||
assertTrue(text.getX1() >= 0 && text.getY1() >= 0);
|
||||
});
|
||||
foundTexts.forEach(
|
||||
text -> {
|
||||
assertNotNull(text.getText());
|
||||
assertTrue(text.getX1() >= 0 && text.getY1() >= 0);
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
@ -485,8 +554,10 @@ class TextFinderTest {
|
||||
textFinder.getText(document);
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
|
||||
assertEquals(1, foundTexts.size(),
|
||||
"Should find exactly one standalone '1', not the ones embedded in other numbers/codes");
|
||||
assertEquals(
|
||||
1,
|
||||
foundTexts.size(),
|
||||
"Should find exactly one standalone '1', not the ones embedded in other numbers/codes");
|
||||
assertEquals("1", foundTexts.get(0).getText());
|
||||
}
|
||||
|
||||
@ -500,14 +571,16 @@ class TextFinderTest {
|
||||
textFinder.getText(document);
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
|
||||
assertTrue(foundTexts.size() >= 3,
|
||||
"Should find multiple instances of '1' including standalone, in '1234', and in 'A1B'");
|
||||
assertTrue(
|
||||
foundTexts.size() >= 3,
|
||||
"Should find multiple instances of '1' including standalone, in '1234', and in 'A1B'");
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should find single characters in various contexts")
|
||||
void findSingleCharacters() throws IOException {
|
||||
String content = "Grade: A. Section B has item A-1. The letter A appears multiple times.";
|
||||
String content =
|
||||
"Grade: A. Section B has item A-1. The letter A appears multiple times.";
|
||||
addTextToPage(content);
|
||||
|
||||
TextFinder textFinder = new TextFinder("A", false, true);
|
||||
@ -522,24 +595,29 @@ class TextFinderTest {
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Should handle digits at word boundaries correctly")
|
||||
@DisplayName("Digits as strict standalone tokens (exclude decimals and suffixes)")
|
||||
void findDigitsAtWordBoundaries() throws IOException {
|
||||
String content = "Numbers: 1, 2, 3. Code: 123. Version: 1.0. Item1 and Item2.";
|
||||
String content =
|
||||
"Numbers: 1, 2, 3. Code: 123. Version: 1.0. Item1 and Item2. Price: 2,50€";
|
||||
addTextToPage(content);
|
||||
|
||||
TextFinder textFinder1 = new TextFinder("1", false, true);
|
||||
textFinder1.getText(document);
|
||||
List<PDFText> foundTexts1 = textFinder1.getFoundTexts();
|
||||
|
||||
assertEquals(1, foundTexts1.size(),
|
||||
"Should find only the standalone '1' at the beginning");
|
||||
assertEquals(
|
||||
1,
|
||||
foundTexts1.size(),
|
||||
"Should find only the standalone '1'; do not count the '1' in '1.0' or in 'Item1'.");
|
||||
|
||||
TextFinder textFinder2 = new TextFinder("2", false, true);
|
||||
textFinder2.getText(document);
|
||||
List<PDFText> foundTexts2 = textFinder2.getFoundTexts();
|
||||
|
||||
assertEquals(1, foundTexts2.size(),
|
||||
"Should find only the standalone '2' in the number list");
|
||||
assertEquals(
|
||||
1,
|
||||
foundTexts2.size(),
|
||||
"Should find only the standalone '2' in the number list");
|
||||
}
|
||||
|
||||
@Test
|
||||
@ -566,8 +644,10 @@ class TextFinderTest {
|
||||
textFinder.getText(document);
|
||||
List<PDFText> foundTexts = textFinder.getFoundTexts();
|
||||
|
||||
assertEquals(2, foundTexts.size(),
|
||||
"Should find both '1' instances despite spacing variations");
|
||||
assertEquals(
|
||||
2,
|
||||
foundTexts.size(),
|
||||
"Should find both '1' instances despite spacing variations");
|
||||
}
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user