Skip to content

Reduce the size of the match string in TextMatches data table #4874

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MBoegers merged 11 commits into from
May 7, 2025
Merged

Reduce the size of the match string in TextMatches data table #4874

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
d44dfc5
Reduce the size of the match string in `TextMatches` data table
knutwannheden Jan 9, 2025
fc37ded
Polish
knutwannheden Jan 9, 2025
d51ea7d
Merge branch 'main' into limited-find-context
knutwannheden Feb 20, 2025
f44d81e
make context size configurable
MBoegers May 6, 2025
a908e22
Merge branch 'main' into limited-find-context
MBoegers May 6, 2025
04741d7
Merge branch 'main' into limited-find-context
MBoegers May 7, 2025
7303d7a
fix test setup
MBoegers May 7, 2025
4e133bb
fix test setup of DeclarativeRecipeTest
MBoegers May 7, 2025
38956b7
Apply suggestions from code review
timtebeek May 7, 2025
d7d3ddf
Merge branch 'main' into limited-find-context
MBoegers May 7, 2025
e39c2a5
rework the truncate logic to be simpler
MBoegers May 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 41 additions & 10 deletions rewrite-core/src/main/java/org/openrewrite/text/Find.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
import lombok.EqualsAndHashCode;
import lombok.Value;
import org.apache.commons.lang3.BooleanUtils;
import org.jetbrains.annotations.NotNull;
Comment thread
timtebeek marked this conversation as resolved.
Outdated
import org.jspecify.annotations.Nullable;
import org.openrewrite.*;
import org.openrewrite.binary.Binary;
Expand Down Expand Up @@ -97,6 +98,14 @@ public String getDescription() {
@Nullable
Boolean description;

@Option(displayName = "Context size for Datatable",
description = "The number of characters to include in the datatable before and after the match. Default `0`, " +
"`-1` indicates that the whole text should be used.",
required = false,
example = "50")
@Nullable
Integer contextSize;

@Override
public String getInstanceName() {
return String.format("Find text `%s`", find);
Expand All @@ -106,6 +115,7 @@ public String getInstanceName() {
public TreeVisitor<?, ExecutionContext> getVisitor() {

TreeVisitor<?, ExecutionContext> visitor = new TreeVisitor<Tree, ExecutionContext>() {

@Override
public Tree visit(@Nullable Tree tree, ExecutionContext ctx) {
SourceFile sourceFile = (SourceFile) requireNonNull(tree);
Expand Down Expand Up @@ -164,24 +174,45 @@ public Tree visit(@Nullable Tree tree, ExecutionContext ctx) {
}

int startLine = lastNewLineIndex + 1;
int endLine = rawText.indexOf('\n', matcher.end());
int endLine = nextNewLineIndex > matcher.end() ? nextNewLineIndex : rawText.indexOf('\n', matcher.end());
if (endLine == -1) {
endLine = rawText.length();
}

//noinspection StringBufferReplaceableByString
textMatches.insertRow(ctx, new TextMatches.Row(
sourceFilePath,
new StringBuilder(endLine - startLine + 3)
.append(rawText, startLine, matchStart)
.append("~~>")
.append(rawText, matchStart, endLine)
.toString()
));
String context = truncateContext(endLine, startLine, matcher, matchStart, rawText);

textMatches.insertRow(ctx, new TextMatches.Row(sourceFilePath, context));
} while (matcher.find());
snippets.add(snippet(rawText.substring(previousEnd)));
return plainText.withText("").withSnippets(snippets);
}

private @NotNull String truncateContext(int endLine, int startLine, Matcher matcher, int matchStart, String rawText) {
Comment thread
timtebeek marked this conversation as resolved.
Outdated
if (contextSize == null || contextSize == 0) {
return "...~~>" + matcher.group() + "...";
}

if (contextSize == -1) {
return rawText.substring(0, matchStart) + "~~>" + rawText.substring(matchStart);
}

StringBuilder context = new StringBuilder(Math.min(endLine - startLine + 3, contextSize * 2 + matcher.group().length() + 3));
if (matchStart - startLine > contextSize) {
context.append("...");
context.append(rawText, matchStart - (contextSize - 3), matchStart);
} else {
context.append(rawText, startLine, matchStart);
}
context.append("~~>");
int matchLength = matcher.group().length();
if (endLine - (matchStart + 3 + matchLength) > contextSize) {
context.append(rawText, matchStart, matchStart + 3 + matchLength + (contextSize - 3));
context.append("...");
} else {
context.append(rawText, matchStart, endLine);
}
return context.toString();
}
};
if (filePattern != null) {
visitor = Preconditions.check(new FindSourceFiles(filePattern), visitor);
Expand Down
2 changes: 1 addition & 1 deletion rewrite-core/src/test/java/org/openrewrite/config/DeclarativeRecipeTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,7 +336,7 @@ void preconditionOnNestedDeclarative() {
void exposesUnderlyingDataTables() {
DeclarativeRecipe dr = new DeclarativeRecipe("org.openrewrite.DeclarativeDataTable", "declarative with data table",
"test", emptySet(), null, URI.create("dummy"), true, Collections.emptyList());
dr.addUninitialized(new Find("sam", null, null, null, null, null, null));
dr.addUninitialized(new Find("sam", null, null, null, null, null, null, null));
dr.initialize(List.of(), Map.of());
assertThat(dr.getDataTableDescriptors()).anyMatch(it -> "org.openrewrite.table.TextMatches".equals(it.getName()));
}
Expand Down
119 changes: 108 additions & 11 deletions rewrite-core/src/test/java/org/openrewrite/text/FindTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ class FindTest implements RewriteTest {
@Test
void regex() {
rewriteRun(
spec -> spec.recipe(new Find("[T\\s]", true, true, null, null, null, null)),
spec -> spec.recipe(new Find("[T\\s]", true, true, null, null, null, null, null)),
text(
"""
This is\ttext.
Expand All @@ -45,7 +45,7 @@ void regex() {
@Test
void dataTable() {
rewriteRun(
spec -> spec.recipe(new Find("text", null, null, null, null, null, null))
spec -> spec.recipe(new Find("text", null, null, null, null, null, null, 50))
.dataTable(TextMatches.Row.class, rows -> {
assertThat(rows).hasSize(1);
assertThat(rows.get(0).getMatch()).isEqualTo("This is ~~>text.");
Expand All @@ -68,7 +68,7 @@ void dataTable() {
@Test
void plainText() {
rewriteRun(
spec -> spec.recipe(new Find("\\s", null, null, null, null, null, null)),
spec -> spec.recipe(new Find("\\s", null, null, null, null, null, null, 50)),
text(
"""
This i\\s text.
Expand All @@ -83,7 +83,7 @@ void plainText() {
@Test
void caseInsensitive() {
rewriteRun(
spec -> spec.recipe(new Find("text", null, null, null, null, "**/foo/**;**/baz/**", null)),
spec -> spec.recipe(new Find("text", null, null, null, null, "**/foo/**;**/baz/**", null, 50)),
dir("foo",
text(
"""
Expand Down Expand Up @@ -115,7 +115,7 @@ void caseInsensitive() {
@Test
void regexBasicMultiLine() {
rewriteRun(
spec -> spec.recipe(new Find("[T\\s]", true, true, true, null, null, null)),
spec -> spec.recipe(new Find("[T\\s]", true, true, true, null, null, null, 50)),
text(
"""
This is\ttext.
Expand All @@ -132,7 +132,7 @@ void regexBasicMultiLine() {
@Test
void regexWithoutMultilineAndDotall() {
rewriteRun(
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, false, false, null, null)),
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, false, false, null, null, 50)),
text(
"""
This is text.
Expand All @@ -148,7 +148,7 @@ void regexWithoutMultilineAndDotall() {
@Test
void regexMatchingWhitespaceWithoutMultilineWithDotall() {
rewriteRun(
spec -> spec.recipe(new Find("One.Two$", true, true, false, true, null, null)),
spec -> spec.recipe(new Find("One.Two$", true, true, false, true, null, null, 50)),
//language=csv
text( // the `.` above matches the space character on the same line
"""
Expand All @@ -163,7 +163,7 @@ void regexMatchingWhitespaceWithoutMultilineWithDotall() {
@Test
void regexWithoutMultilineAndWithDotAll() {
rewriteRun(
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, false, true, null, null)),
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, false, true, null, null, 50)),
text(
"""
This is text.
Expand All @@ -186,7 +186,7 @@ void regexWithoutMultilineAndWithDotAll() {
@Test
void regexWithMultilineAndWithoutDotall() {
rewriteRun(
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, true, false, null, null)),
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, true, false, null, null, 50)),
text(
"""
This is text.
Expand All @@ -209,7 +209,7 @@ void regexWithMultilineAndWithoutDotall() {
@Test
void regexWithBothMultilineAndDotAll() {
rewriteRun(
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, true, true, null, null)),
spec -> spec.recipe(new Find("^This.*below\\.$", true, true, true, true, null, null, 50)),
text(
"""
The first line.
Expand All @@ -232,7 +232,7 @@ void regexWithBothMultilineAndDotAll() {
@Test
void description() {
rewriteRun(
spec -> spec.recipe(new Find("text", null, null, null, null, null, true)),
spec -> spec.recipe(new Find("text", null, null, null, null, null, true, 50)),
text(
"""
This is text.
Expand All @@ -243,4 +243,101 @@ void description() {
)
);
}

@Test
void longLine() {
rewriteRun(
spec -> spec.recipe(new Find("very", null, null, null, null, null, null, 50))
.dataTable(TextMatches.Row.class, rows -> {
assertThat(rows).hasSize(18);
assertThat(rows).satisfiesExactly(
r -> assertThat(r.getMatch()).isEqualTo("This is a ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("...is a very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, ..."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very l..."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("...ery, very, very, very, very, very, very, very, ~~>very long line.")
);
}),
text(
"""
This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line.
""",
"""
This is a ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very long line.
"""
)
);
}

@Test
void justMatch() {
rewriteRun(
spec -> spec.recipe(new Find("very", null, null, null, null, null, null, null))
.dataTable(TextMatches.Row.class, rows -> {
assertThat(rows).hasSize(18);
assertThat(rows).allSatisfy(
r -> assertThat(r.getMatch()).isEqualTo("...~~>very...")
);
}),
text(
"""
This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line.
""",
"""
This is a ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very long line.
"""
)
);
}

@Test
void noTruncate() {
rewriteRun(
spec -> spec.recipe(new Find("very", null, null, null, null, null, null, -1))
.dataTable(TextMatches.Row.class, rows -> {
assertThat(rows).hasSize(18);
assertThat(rows).satisfiesExactly(
r -> assertThat(r.getMatch()).isEqualTo("This is a ~~>very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, ~~>very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, ~~>very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, ~~>very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, very, ~~>very, very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, very, very, ~~>very, very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, ~~>very, very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, ~~>very, very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, ~~>very, very long line."),
r -> assertThat(r.getMatch()).isEqualTo("This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, ~~>very long line.")
);
}),
text(
"""
This is a very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very, very long line.
""",
"""
This is a ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very, ~~>very long line.
"""
)
);
}
}
Loading
⚡