Skip to content

new!: added snakeCaseWithOptions, updated snakeCase to use it, and deprecated snakeCaseWithSep/Keep #13

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
merged 1 commit into from
Feb 16, 2025
Merged

new!: added snakeCaseWithOptions, updated snakeCase to use it, and deprecated snakeCaseWithSep/Keep #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
299 changes: 84 additions & 215 deletions src/main/java/com/github/sttk/stringcase/StringCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -664,83 +664,88 @@ public static String pascalCaseWithKeep(String input, String kept) {
}

/**
* Converts a string to snake case.
* Converts the input string to snake case with the specified options.
*
* This method takes a string as its argument, then returns a string of which
* the case style is snake case.
*
* This method targets the upper and lower cases of ASCII alphabets for
* capitalization, and all characters except ASCII alphabets and ASCII
* numbers are eliminated as word separators.
*
* <pre>{@code
* String snake = StringCase.snakeCase("fooBarBaz");
* // => "foo_bar_baz"
* }</pre>
*
* @param input A string to be converted.
* @param input The input string.
* @param opts The options with specifies the ways of case conversion.
* @return A string converted to snake case.
*/
public static String snakeCase(String input) {
var result = new CodepointBuffer(input.length() + input.length() / 2);
public static String snakeCaseWithOptions(String input, Options opts) {
var result = new CodepointBuffer(input.length());

final int UNDERSCORE = 0x5f;

enum ChIs {
FirstOfStr,
NextOfUpper,
NextOfContdUpper,
NextOfSepMark,
NextOfKeepedMark,
Others,
}
var flag = ChIs.FirstOfStr;

int[] sepChs = null;
if (opts.separators != null && !opts.separators.isEmpty()) {
sepChs = opts.separators.codePoints().toArray();
Arrays.sort(sepChs);
}

int[] keptChs = null;
if (opts.keep != null && !opts.keep.isEmpty()) {
keptChs = opts.keep.codePoints().toArray();
Arrays.sort(keptChs);
}

for (int ch : input.codePoints().toArray()) {
if (Ascii.isUpperCase(ch)) {
switch (flag) {
case ChIs.FirstOfStr:
if (flag == ChIs.FirstOfStr) {
result.append(Ascii.toLowerCase(ch));
flag = ChIs.NextOfUpper;
break;
case ChIs.NextOfUpper:
case ChIs.NextOfContdUpper:
} else if (flag == ChIs.NextOfUpper || flag == ChIs.NextOfContdUpper ||
(!opts.separateAfterNonAlphabets && flag == ChIs.NextOfKeptMark)) {
result.append(Ascii.toLowerCase(ch));
flag = ChIs.NextOfContdUpper;
break;
default:
} else {
result.append(UNDERSCORE, Ascii.toLowerCase(ch));
flag = ChIs.NextOfUpper;
break;
}
} else if (Ascii.isLowerCase(ch)) {
switch (flag) {
case ChIs.NextOfContdUpper:
if (flag == ChIs.NextOfContdUpper) {
int prev = result.last();
result.replaceLast(UNDERSCORE, prev, ch);
break;
case ChIs.NextOfSepMark:
case ChIs.NextOfKeepedMark:
} else if (flag == ChIs.NextOfSepMark ||
(opts.separateAfterNonAlphabets && flag == ChIs.NextOfKeptMark)) {
result.append(UNDERSCORE, ch);
break;
default:
} else {
result.append(ch);
break;
}
flag = ChIs.Others;
} else if (Ascii.isDigit(ch)) {
switch (flag) {
case ChIs.NextOfSepMark:
result.append(UNDERSCORE, ch);
break;
default:
result.append(ch);
break;
}
flag = ChIs.NextOfKeepedMark;
} else {
if (flag != ChIs.FirstOfStr) {
flag = ChIs.NextOfSepMark;
var isKeptChar = false;
if (Ascii.isDigit(ch)) {
isKeptChar = true;
} else if (sepChs != null) {
if (Arrays.binarySearch(sepChs, ch) < 0) {
isKeptChar = true;
}
} else if (keptChs != null) {
if (Arrays.binarySearch(keptChs, ch) >= 0) {
isKeptChar = true;
}
}

if (isKeptChar) {
if (opts.separateBeforeNonAlphabets) {
if (flag == ChIs.FirstOfStr || flag == ChIs.NextOfKeptMark) {
result.append(ch);
} else {
result.append(UNDERSCORE, ch);
}
} else {
if (flag != ChIs.NextOfSepMark) {
result.append(ch);
} else {
result.append(UNDERSCORE, ch);
}
}
flag = ChIs.NextOfKeptMark;
} else {
if (flag != ChIs.FirstOfStr) {
flag = ChIs.NextOfSepMark;
}
}
}
}
Expand All @@ -749,180 +754,44 @@ enum ChIs {
}

/**
* Converts a string to snake case using the specified characters as
* separators.
*
* This method takes a string as its argument, then returns a strin` of which
* the case style is snake case.
*
* This method targets only the upper and lower cases of ASCII alphabets for
* capitalization, and the characters specified as the second argument of
* this method are regarded as word separators and are replaced to
* underscores.
*
* <pre>{@code
* String snake = StringCase.snakeCaseWithSep("foo-Bar100%Baz", "- ");
* // => "foo_bar100%_baz"
* }</pre>
* Converts the input string to snake case.
* <p>
* It treats the end of a sequence of non-alphabetical characters as a word boundary, but not
* the beginning.
*
* @param input A string to be converted.
* @param seps A string that consists of characters that are word
* separators.
* @param input The input string.
* @return A string converted to snake case.
*/
public static String snakeCaseWithSep(String input, String seps) {
var result = new CodepointBuffer(input.length() + input.length() / 2);

final int UNDERSCORE = 0x5f;

var sepChs = seps.codePoints().toArray();
Arrays.sort(sepChs);

enum ChIs {
FirstOfStr,
NextOfUpper,
NextOfContdUpper,
NextOfSepMark,
NextOfKeepedMark,
Others,
}
var flag = ChIs.FirstOfStr;

for (int ch : input.codePoints().toArray()) {
if (Arrays.binarySearch(sepChs, ch) >= 0) {
if (flag != ChIs.FirstOfStr) {
flag = ChIs.NextOfSepMark;
}
} else if (Ascii.isUpperCase(ch)) {
switch (flag) {
case ChIs.FirstOfStr:
result.append(Ascii.toLowerCase(ch));
flag = ChIs.NextOfUpper;
break;
case ChIs.NextOfUpper:
case ChIs.NextOfContdUpper:
result.append(Ascii.toLowerCase(ch));
flag = ChIs.NextOfContdUpper;
break;
default:
result.append(UNDERSCORE, Ascii.toLowerCase(ch));
flag = ChIs.NextOfUpper;
break;
}
} else if (Ascii.isLowerCase(ch)) {
switch (flag) {
case ChIs.NextOfContdUpper:
int prev = result.last();
result.replaceLast(UNDERSCORE, prev, ch);
break;
case ChIs.NextOfSepMark:
case ChIs.NextOfKeepedMark:
result.append(UNDERSCORE, ch);
break;
default:
result.append(ch);
break;
}
flag = ChIs.Others;
} else {
if (flag == ChIs.NextOfSepMark) {
result.append(UNDERSCORE, ch);
} else {
result.append(ch);
}
flag = ChIs.NextOfKeepedMark;
}
}

return result.toString();
public static String snakeCase(String input) {
return snakeCaseWithOptions(input, new Options(false, true, null, null));
}

/**
* Converts a string to snake case using characters other than the specified
* characters as separators.
*
* This method takes a string as its argument, then returns a string of which
* the case style is snake case.
* Converts the input string to snake case with the specified separator characters.
*
* This method targets only the upper and lower cases of ASCII alphabets for
* capitalization, and the characters other than the specified characters as
* the second argument of this method are regarded as word separators and are
* replaced to underscores.
* @param input The input string.
* @param seps The symbol characters to be treated as separators.
* @return A string converted to snake case.
*
* <pre>{@code
* let snake = stringcase::snake_case_with_keep("foo-bar100%baz", "%");
* // => "foo_bar100%_baz"
* }</pre>
* @deprecated Should use {@link #snakeCaseWithOptions} instead
*/
@Deprecated
public static String snakeCaseWithSep(String input, String seps) {
return snakeCaseWithOptions(input, new Options(false, true, seps, null));
}

/**
* Converts the input string to snake case with the specified characters to be kept.
*
* @param input A string to be converted.
* @param keeped A string that consists of characters that are not word
* separators.
* @param input The input string.
* @param kept The symbol characters not to be treated as separators.
* @return A string converted to snake case.
*
* @deprecated Should use {@link #snakeCaseWithOptions} instead
*/
public static String snakeCaseWithKeep(String input, String keeped) {
var result = new CodepointBuffer(input.length() + input.length() / 2);

final int UNDERSCORE = 0x5f;

var keepChs = keeped.codePoints().toArray();
Arrays.sort(keepChs);

enum ChIs {
FirstOfStr,
NextOfUpper,
NextOfContdUpper,
NextOfSepMark,
NextOfKeepedMark,
Others,
}
var flag = ChIs.FirstOfStr;

for (int ch : input.codePoints().toArray()) {
if (Ascii.isUpperCase(ch)) {
switch (flag) {
case ChIs.FirstOfStr:
result.append(Ascii.toLowerCase(ch));
flag = ChIs.NextOfUpper;
break;
case ChIs.NextOfUpper:
case ChIs.NextOfContdUpper:
result.append(Ascii.toLowerCase(ch));
flag = ChIs.NextOfContdUpper;
break;
default:
result.append(UNDERSCORE, Ascii.toLowerCase(ch));
flag = ChIs.NextOfUpper;
}
} else if (Ascii.isLowerCase(ch)) {
switch (flag) {
case ChIs.NextOfContdUpper:
int prev = result.last();
result.replaceLast(UNDERSCORE, prev, ch);
break;
case ChIs.NextOfSepMark:
case ChIs.NextOfKeepedMark:
result.append(UNDERSCORE, ch);
break;
default:
result.append(ch);
break;
}
flag = ChIs.Others;
} else if (Ascii.isDigit(ch) || Arrays.binarySearch(keepChs, ch) >= 0) {
if (flag == ChIs.NextOfSepMark) {
result.append(UNDERSCORE, ch);
} else {
result.append(ch);
}
flag = ChIs.NextOfKeepedMark;
} else {
if (flag != ChIs.FirstOfStr) {
flag = ChIs.NextOfSepMark;
}
}
}

return result.toString();
@Deprecated
public static String snakeCaseWithKeep(String input, String kept) {
return snakeCaseWithOptions(input, new Options(false, true, null, kept));
}

/**
Expand Down
Loading