Skip to content

Reduce duplication between code and snippet generation #3127

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

Open
ielatif wants to merge 4 commits into
base: main
Choose a base branch
from
+115 −128
Open

Reduce duplication between code and snippet generation #3127

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7608000
Reduce duplication between code and snippet generation
ielatif Dec 3, 2025
a93b16d
Resolve complaints from RevApi
mpkorstanje Dec 8, 2025
99b68f0
Move GherkinKeywordNormalizer to snippets package
mpkorstanje Dec 8, 2025
fdd4cdc
Code review + Units tests
ielatif Dec 8, 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
65 changes: 65 additions & 0 deletions cucumber-core/src/main/java/io/cucumber/core/snippets/GherkinKeywordNormalizer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
package io.cucumber.core.snippets;

import org.apiguardian.api.API;

import java.text.Normalizer;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.stream.IntStream;

import static java.util.stream.Collectors.joining;

@API(status = API.Status.INTERNAL)
public final class GherkinKeywordNormalizer {

private GherkinKeywordNormalizer() {
/* no-op */
}

public static String normalizeKeyword(String language, String keyword) {
// Exception: Use the symbol names for the Emoj language.
// Emoji are not legal identifiers in Java.
if ("em".equals(language)) {
return normalizeEmojiKeyword(keyword);
}
return normalizeKeyword(keyword);
}

public static String normalizeLanguage(String language) {
return language.replaceAll("[\\s-]", "_").toLowerCase();
}

public static String capitalize(String str) {
Copy link
Contributor

@mpkorstanje mpkorstanje Dec 8, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This doesn't quite belong. Please make private and duplicate as needed.

return str.substring(0, 1).toUpperCase() + str.substring(1);
}

private static String normalizeKeyword(String keyword) {
return normalize(keyword.replaceAll("[\\s',!\u00AD’]", ""));
}

private static String normalizeEmojiKeyword(String keyword) {
String titleCasedName = getCodePoints(keyword).mapToObj(Character::getName)
.map(s -> s.split(" "))
.flatMap(Arrays::stream)
.map(String::toLowerCase)
.map(GherkinKeywordNormalizer::capitalize)
.collect(joining(" "));
return normalizeKeyword(titleCasedName);
}

private static String normalize(CharSequence s) {
return Normalizer.normalize(s, Normalizer.Form.NFC);
}

private static IntStream getCodePoints(String s) {
int length = s.length();
List<Integer> codePoints = new ArrayList<>();
for (int offset = 0; offset < length;) {
int codepoint = s.codePointAt(offset);
codePoints.add(codepoint);
offset += Character.charCount(codepoint);
}
return codePoints.stream().mapToInt(value -> value);
}
}
50 changes: 2 additions & 48 deletions cucumber-core/src/main/java/io/cucumber/core/snippets/SnippetGenerator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,20 +12,16 @@
import io.cucumber.plugin.event.StepArgument;

import java.lang.reflect.Type;
import java.text.Normalizer;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
import java.util.Optional;
import java.util.regex.Pattern;
import java.util.stream.Collectors;
import java.util.stream.IntStream;
import java.util.stream.Stream;

import static io.cucumber.core.snippets.GherkinKeywordNormalizer.normalizeKeyword;
import static io.cucumber.core.snippets.SnippetType.CAMELCASE;
import static java.util.stream.Collectors.joining;

public final class SnippetGenerator {

Expand Down Expand Up @@ -72,7 +68,7 @@ private String createSnippet(
List<String> parameterNames = toParameterNames(expression, parameterNameGenerator);
Map<String, Type> arguments = arguments(step, parameterNames, expression.getParameterTypes());
return snippet.template().format(new String[] {
getNormalizedKeyWord(language, keyword),
normalizeKeyword(language, keyword),
snippet.escapePattern(source),
functionName,
snippet.arguments(arguments),
Expand All @@ -88,48 +84,6 @@ private List<String> toParameterNames(GeneratedExpression expression, Identifier
.collect(Collectors.toList());
}

private static String capitalize(String str) {
return str.substring(0, 1).toUpperCase() + str.substring(1);
}

private static String getNormalizedKeyWord(String language, String keyword) {
// Exception: Use the symbol names for the Emoj language.
// Emoji are not legal identifiers in Java.
if ("em".equals(language)) {
return getNormalizedEmojiKeyWord(keyword);
}
return getNormalizedKeyWord(keyword);
}

private static String getNormalizedEmojiKeyWord(String keyword) {
String titleCasedName = getCodePoints(keyword).mapToObj(Character::getName)
.map(s -> s.split(" "))
.flatMap(Arrays::stream)
.map(String::toLowerCase)
.map(SnippetGenerator::capitalize)
.collect(joining(" "));
return getNormalizedKeyWord(titleCasedName);
}

private static IntStream getCodePoints(String s) {
int length = s.length();
List<Integer> codePoints = new ArrayList<>();
for (int offset = 0; offset < length;) {
int codepoint = s.codePointAt(offset);
codePoints.add(codepoint);
offset += Character.charCount(codepoint);
}
return codePoints.stream().mapToInt(value -> value);
}

private static String getNormalizedKeyWord(String keyword) {
return normalize(keyword.replaceAll("[\\s',!\u00AD’]", ""));
}

static String normalize(CharSequence s) {
return Normalizer.normalize(s, Normalizer.Form.NFC);
}

private String functionName(String sentence, IdentifierGenerator functionNameGenerator) {
String functionName = Stream.of(sentence)
.map(DEFAULT_ARGUMENT_PATTERN::replaceMatchesWithSpace)
Expand Down
46 changes: 5 additions & 41 deletions cucumber-java/src/codegen/java/GenerateI18n.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,18 +9,17 @@
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.text.Normalizer;
import java.util.Arrays;
import java.util.Collections;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Locale;
import java.util.Map;

import static io.cucumber.core.snippets.GherkinKeywordNormalizer.normalizeKeyword;
import static io.cucumber.core.snippets.GherkinKeywordNormalizer.normalizeLanguage;
import static java.nio.file.Files.newBufferedWriter;
import static java.nio.file.StandardOpenOption.CREATE;
import static java.nio.file.StandardOpenOption.TRUNCATE_EXISTING;
import static java.util.stream.Collectors.joining;

/* This class generates the cucumber-java Interfaces and package-info
* based on the languages and keywords from the GherkinDialects
Expand Down Expand Up @@ -79,8 +78,8 @@ private void writeKeyWordAnnotations(GherkinDialect dialect) {
}

private void writeKeyWordAnnotation(GherkinDialect dialect, String keyword) {
String normalizedLanguage = getNormalizedLanguage(dialect);
String normalizedKeyword = getNormalizedKeyWord(dialect, keyword);
String normalizedLanguage = normalizeLanguage(dialect.getLanguage());
String normalizedKeyword = normalizeKeyword(dialect.getLanguage(), keyword);

Map<String, String> binding = new LinkedHashMap<>();
binding.put("lang", normalizedLanguage);
Expand All @@ -103,39 +102,8 @@ private void writeKeyWordAnnotation(GherkinDialect dialect, String keyword) {
}
}

private static String capitalize(String s) {
return s.substring(0, 1).toUpperCase() + s.substring(1);
}

private static String getNormalizedKeyWord(GherkinDialect dialect, String keyword) {
// Exception: Use the symbol names for the Emoj language.
// Emoji are not legal identifiers in Java.
if (dialect.getLanguage().equals("em")) {
return getNormalizedEmojiKeyWord(keyword);
}
return getNormalizedKeyWord(keyword);
}

private static String getNormalizedEmojiKeyWord(String keyword) {
String titleCasedName = keyword.codePoints().mapToObj(Character::getName)
.map(s -> s.split(" "))
.flatMap(Arrays::stream)
.map(String::toLowerCase)
.map(DialectWriter::capitalize)
.collect(joining(" "));
return getNormalizedKeyWord(titleCasedName);
}

private static String getNormalizedKeyWord(String keyword) {
return normalize(keyword.replaceAll("[\\s',!\u00AD’]", ""));
}

private static String normalize(CharSequence s) {
return Normalizer.normalize(s, Normalizer.Form.NFC);
}

private void writePackageInfo(GherkinDialect dialect) {
String normalizedLanguage = getNormalizedLanguage(dialect);
String normalizedLanguage = normalizeLanguage(dialect.getLanguage());
String languageName = dialect.getName();
if (!dialect.getName().equals(dialect.getNativeName())) {
languageName += " - " + dialect.getNativeName();
Expand All @@ -155,9 +123,5 @@ private void writePackageInfo(GherkinDialect dialect) {
}
}

private static String getNormalizedLanguage(GherkinDialect dialect) {
return dialect.getLanguage().replaceAll("[\\s-]", "_").toLowerCase();
}

}
}
45 changes: 5 additions & 40 deletions cucumber-java8/src/codegen/java/GenerateI18n.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,18 +9,18 @@
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.text.Normalizer;
import java.util.Arrays;
import java.util.Collections;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Locale;
import java.util.Map;

import static io.cucumber.core.snippets.GherkinKeywordNormalizer.capitalize;
import static io.cucumber.core.snippets.GherkinKeywordNormalizer.normalizeKeyword;
import static io.cucumber.core.snippets.GherkinKeywordNormalizer.normalizeLanguage;
import static java.nio.file.Files.newBufferedWriter;
import static java.nio.file.StandardOpenOption.CREATE;
import static java.nio.file.StandardOpenOption.TRUNCATE_EXISTING;
import static java.util.stream.Collectors.joining;
import static java.util.stream.Collectors.toList;

/* This class generates the cucumber-java Interfaces and package-info
Expand Down Expand Up @@ -69,7 +69,7 @@ void writeDialect(GherkinDialect dialect) {
}

private void writeInterface(GherkinDialect dialect) {
String normalizedLanguage = getNormalizedLanguage(dialect);
String normalizedLanguage = normalizeLanguage(dialect.getLanguage());
String languageName = dialect.getName();
if (!dialect.getName().equals(dialect.getNativeName())) {
languageName += " - " + dialect.getNativeName();
Expand Down Expand Up @@ -98,43 +98,8 @@ private static List<String> extractKeywords(GherkinDialect dialect) {
.filter(it -> !it.contains(String.valueOf('*')))
.filter(it -> !it.matches("^\\d.*"))
.distinct()
.map(keyword -> getNormalizedKeyWord(dialect, keyword))
.map(keyword -> normalizeKeyword(dialect.getLanguage(), keyword))
.collect(toList());
}

private static String capitalize(String str) {
return str.substring(0, 1).toUpperCase() + str.substring(1);
}

private static String getNormalizedKeyWord(GherkinDialect dialect, String keyword) {
// Exception: Use the symbol names for the Emoj language.
// Emoji are not legal identifiers in Java.
if (dialect.getLanguage().equals("em")) {
return getNormalizedEmojiKeyWord(keyword);
}
return getNormalizedKeyWord(keyword);
}

private static String getNormalizedEmojiKeyWord(String keyword) {
String titleCasedName = keyword.codePoints().mapToObj(Character::getName)
.map(s -> s.split(" "))
.flatMap(Arrays::stream)
.map(String::toLowerCase)
.map(DialectWriter::capitalize)
.collect(joining(" "));
return getNormalizedKeyWord(titleCasedName);
}

private static String getNormalizedKeyWord(String keyword) {
return normalize(keyword.replaceAll("[\\s',!\u00AD’]", ""));
}

static String normalize(CharSequence s) {
return Normalizer.normalize(s, Normalizer.Form.NFC);
}

private static String getNormalizedLanguage(GherkinDialect dialect) {
return dialect.getLanguage().replaceAll("[\\s-]", "_").toLowerCase();
}
}
}