Message ID | 20220302142608.2754709-2-jaydeepjd.8914@gmail.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | userdiff: add builtin driver for kotlin language | expand |
Am 02.03.22 um 15:26 schrieb Jaydeep P Das: > diff --git a/t/t4034/kotlin/expect b/t/t4034/kotlin/expect > new file mode 100644 > index 0000000000..7062b67319 > --- /dev/null > +++ b/t/t4034/kotlin/expect > @@ -0,0 +1,34 @@ > +<BOLD>diff --git a/pre b/post<RESET> > +<BOLD>index 3cfa271..20d26cc 100644<RESET> > +<BOLD>--- a/pre<RESET> > +<BOLD>+++ b/post<RESET> > +<CYAN>@@ -1,21 +1,21 @@<RESET> > +println("Hello World<RED>!\n<RESET><GREEN>?<RESET>") > +<GREEN>(<RESET>1<GREEN>) (<RESET>-1e10<GREEN>) (<RESET>0xabcdef<GREEN>)<RESET> '<RED>x<RESET><GREEN>y<RESET>' > +[<RED>a<RESET><GREEN>x<RESET>] <RED>a<RESET><GREEN>x<RESET>-><RED>b a<RESET><GREEN>y x<RESET>.<RED>b<RESET><GREEN>y<RESET> > +!<RED>a a<RESET><GREEN>x x<RESET>.inv() <RED>a<RESET><GREEN>x<RESET>*<RED>b a<RESET><GREEN>y x<RESET>&<RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET>*<RED>b a<RESET><GREEN>y x<RESET>/<RED>b a<RESET><GREEN>y x<RESET>%<RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET>+<RED>b a<RESET><GREEN>y x<RESET>-<RED>b<RESET><GREEN>y<RESET> > +a <RED>shr<RESET><GREEN>shl<RESET> b > +<RED>a<RESET><GREEN>x<RESET><<RED>b a<RESET><GREEN>y x<RESET><=<RED>b a<RESET><GREEN>y x<RESET>><RED>b a<RESET><GREEN>y x<RESET>>=<RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET>==<RED>b a<RESET><GREEN>y x<RESET>!=<RED>b a<RESET><GREEN>y x<RESET>===<RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET> and <RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET>^<RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET> or <RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET>&&<RED>b a<RESET><GREEN>y x<RESET>||<RED>b<RESET> > +<RED>a<RESET><GREEN>y<RESET> > +<GREEN>x<RESET>=<RED>b a<RESET><GREEN>y x<RESET>+=<RED>b a<RESET><GREEN>y x<RESET>-=<RED>b a<RESET><GREEN>y x<RESET>*=<RED>b a<RESET><GREEN>y x<RESET>/=<RED>b a<RESET><GREEN>y x<RESET>%=<RED>b a<RESET><GREEN>y x<RESET><<=<RED>b a<RESET><GREEN>y x<RESET>>>=<RED>b a<RESET><GREEN>y x<RESET>&=<RED>b a<RESET><GREEN>y x<RESET>^=<RED>b a<RESET><GREEN>y x<RESET>|=<RED>b<RESET><GREEN>y<RESET> > +a<RED>=<RESET><GREEN>+=<RESET>b c<RED>+=<RESET><GREEN>=<RESET>d e<RED>-=<RESET><GREEN><=<RESET>f g<RED>*=<RESET><GREEN>>=<RESET>h i<RED>/=<RESET><GREEN>/<RESET>j k<RED>%=<RESET><GREEN>%<RESET>l m<RED><<=<RESET><GREEN><<<RESET>n o<RED>>>=<RESET><GREEN>>><RESET>p q<RED>&=<RESET><GREEN>&<RESET>r s<RED>^=<RESET><GREEN>^<RESET>t u<RED>|=<RESET><GREEN>|<RESET>v > +a<RED><<=<RESET><GREEN><=<RESET>b > +a<RED>||<RESET><GREEN>|<RESET>b a<RED>&&<RESET><GREEN>&<RESET>b > +<RED>a<RESET><GREEN>x<RESET>,y > +--a<RED>==<RESET><GREEN>!=<RESET>--b > +a++<RED>==<RESET><GREEN>!=<RESET>++b > +<RED>0xFF_EC_DE_5E 0b100_000 100_000<RESET><GREEN>0xFF_E1_DE_5E 0b100_100 200_000<RESET> Many of the a->x, b->y changes are redundant IMHO, but they do not hurt. This looks good. > diff --git a/userdiff.c b/userdiff.c > index 8578cb0d12..bb701100c6 100644 > --- a/userdiff.c > +++ b/userdiff.c > @@ -168,6 +168,16 @@ PATTERNS("java", > "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?" > "|[-+*/<>%&^|=!]=" > "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"), > +PATTERNS("kotlin", > + "^[ \t]*(([a-z]+[ \t]+)*(fun|class|interface)[ \t]+.*)$", > + /* -- */ > + "[_]?[a-zA-Z][a-zA-Z0-9_]*" > + /* hexadecimal and binary numbers */ > + "|0[xXbB][0-9a-fA-F_]+[lLuU]*" > + /* integers and floats */ > + "|[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*" > + /* unary and binary operators */ > + "|[-+*/<>%&^|=!]?=(=)?|--|\\+\\+|<<?=?|>>?=?|&&?|[|]?\\||\\|->\\*?|\\.\\*"), Some of these sub-expressions match single-character operators, but that does not hurt. How many tokens will the word-regex find in the expression X.e+200UL? .e+200UL is a single token. Also, X.Find consists of the three tokens X .F ind. It's most easily fixed by requiring a digit before the fullstop. But if floatingpoint numbers can begin with a fullstop, then we need a second expression that requires a digit after a leading fullstop. > PATTERNS("markdown", > "^ {0,3}#{1,6}[ \t].*", > /* -- */ -- Hannes
How about modifying the number match regex to: `[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` ? The `[^a-zA-Z]` in the end would make sure to not match the `.F` in `X.Find`. Additionally, we can add another regex for matching just the method calls: `[.][a-zA-Z()0-9]+` Both of these changes would make word_regex match 2 tokens in X.Find() : X and .Find() (Here X can be any valid identifier name) > How many tokens will the word-regex find in the expression X.e+200UL? > .e+200UL is a single token. > It's most easily fixed by requiring a digit before the fullstop. But if > floatingpoint numbers can begin with a fullstop, then we need a second > expression that requires a digit after a leading fullstop. But that syntax would be wrong. I tried making a condition like you said, but it always ended up breaking something else(like breaking 2.e+200UL into 2, .e, + and 200UL) Also, I realized I did a bit of mistake in the identifier regex. Both _abc and __abc are valid identifiers. _3432, __3232 are valid identifiers too.(not numbers) The previous regex matched only one `_`, so in the next patch, I plan to implement the following regex: Identifier: `([_]*[a-zA-Z]|[_]+[0-9]+)[a-zA-Z0-9_]*` Numbers: `[0-9_.]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` (It makes sure that in X.Find, .F is not matched ) Additionally, An extra regex for method calls: `[.][a-zA-Z()0-9]+` What do you think? Thanks, Jaydeep.
On Thu, Mar 03 2022, Jaydeep Das wrote: > How about modifying the number match regex to: > > `[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` ? > > The `[^a-zA-Z]` in the end would make sure to not match > the `.F` in `X.Find`. > > Additionally, we can add another regex for matching just > the method calls: > > `[.][a-zA-Z()0-9]+` > > Both of these changes would make word_regex match 2 tokens in > X.Find() : X and .Find() (Here X can be any valid identifier name) > > >> How many tokens will the word-regex find in the expression X.e+200UL? >> .e+200UL is a single token. > It's most easily fixed by requiring a digit before the fullstop. But if >> floatingpoint numbers can begin with a fullstop, then we need a second >> expression that requires a digit after a leading fullstop. > > But that syntax would be wrong. I tried making a condition like you said, > but it always ended up breaking something else(like breaking 2.e+200UL into 2, .e, + and 200UL) > > Also, I realized I did a bit of mistake in the identifier regex. > Both _abc and __abc are valid identifiers. _3432, __3232 are valid identifiers too.(not numbers) > > The previous regex matched only one `_`, so in the next patch, > I plan to implement the following regex: > > Identifier: `([_]*[a-zA-Z]|[_]+[0-9]+)[a-zA-Z0-9_]*` > > Numbers: `[0-9_.]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` > (It makes sure that in X.Find, .F is not matched ) > > Additionally, An extra regex for method calls: > > `[.][a-zA-Z()0-9]+` > > What do you think? Just a small note on rx syntax> [.] can be handy to escape "." (but you can also use "\\.", but that's arguably not as easy to read. But there's no reason to use [_]* over just _*.. (Also, I have an in-flight change to userdiff.c that would conflict, but I wonder if it wouldn't be handy to make the word_regex a "struct userdiff_funcname". Then we could specify icase flags, which in this case would make it a lot easier to read).
Jaydeep Das <jaydeepjd.8914@gmail.com> writes: > How about modifying the number match regex to: > > `[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` ? > > The `[^a-zA-Z]` in the end would make sure to not match > the `.F` in `X.Find`. Do we want to match "foo.F<EOL>"? If requiring at least one non-alpha after [fFlLuU]* is OK, then please ignore this message ;-) Thanks.
Am 03.03.22 um 12:41 schrieb Jaydeep Das: > How about modifying the number match regex to: > > `[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` ? > > The `[^a-zA-Z]` in the end would make sure to not match > the `.F` in `X.Find`. No, you cannot do that, because then in X.u+1 you have three tokens X .u+ 1, which you do not want, either. > Additionally, we can add another regex for matching just > the method calls: > > `[.][a-zA-Z()0-9]+` > > Both of these changes would make word_regex match 2 tokens in > X.Find() : X and .Find() (Here X can be any valid identifier name) Well, you can do that. But I would not do that if it is allowed to have a blank between the fullstop and a method name. >> How many tokens will the word-regex find in the expression X.e+200UL? >> .e+200UL is a single token. > It's most easily fixed by requiring a >> digit before the fullstop. But if >> floatingpoint numbers can begin with a fullstop, then we need a second >> expression that requires a digit after a leading fullstop. > > But that syntax would be wrong. I tried making a condition like you said, > but it always ended up breaking something else(like breaking 2.e+200UL > into 2, .e, + and 200UL) > > Also, I realized I did a bit of mistake in the identifier regex. > Both _abc and __abc are valid identifiers. _3432, __3232 are valid > identifiers too.(not numbers) > > The previous regex matched only one `_`, so in the next patch, > I plan to implement the following regex: > > Identifier: `([_]*[a-zA-Z]|[_]+[0-9]+)[a-zA-Z0-9_]*` But then you can use the regex you had in the first round: [a-zA-Z_][a-zA-Z0-9_]* > > Numbers: `[0-9_.]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` > (It makes sure that in X.Find, .F is not matched ) > > Additionally, An extra regex for method calls: > > `[.][a-zA-Z()0-9]+` > > What do you think? Have a look at the regex in the cpp driver. I think we need something like this: /* integers floatingpoint numbers */ "|[0-9][0-9_.]*([Ee][*-]?[0-9]+)?[FfLl]*" /* floatingpoint numbers that begin with a decimal point */ "|[.][0-9][0-9_]*([Ee][*-]?[0-9]+)?[FfLl]*" Drop the second option if numbers such as .5 are invalid syntax in Kotlin. -- Hannes
On 3/4/22 01:34, Johannes Sixt wrote: > Am 03.03.22 um 12:41 schrieb Jaydeep Das: >> How about modifying the number match regex to: >> >> `[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` ? >> >> The `[^a-zA-Z]` in the end would make sure to not match >> the `.F` in `X.Find`. > No, you cannot do that, because then in X.u+1 you have three tokens X > .u+ 1, which you do not want, either. If X is an integer here, then In C/C++ 2.f is equivalent to 2.000000 However in Kotlin 2.f is invalid syntax. 2.0f is valid. So is implementing a proper regex for invalid syntax really necessary? > But then you can use the regex you had in the first round: > > [a-zA-Z_][a-zA-Z0-9_]* Right. I will change that. >> Numbers: `[0-9_.]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` >> (It makes sure that in X.Find, .F is not matched ) >> >> Additionally, An extra regex for method calls: >> >> `[.][a-zA-Z()0-9]+` >> >> What do you think? > > Have a look at the regex in the cpp driver. I think we need something > like this: > > /* integers floatingpoint numbers */ > "|[0-9][0-9_.]*([Ee][*-]?[0-9]+)?[FfLl]*" > /* floatingpoint numbers that begin with a decimal point */ > "|[.][0-9][0-9_]*([Ee][*-]?[0-9]+)?[FfLl]*" > Drop the second option if numbers such as .5 are invalid syntax in Kotlin. .5 is valid syntax in Kotlin. -- Thanks, Jaydeep.
Am 04.03.22 um 13:28 schrieb Jaydeep Das: > On 3/4/22 01:34, Johannes Sixt wrote: >> Am 03.03.22 um 12:41 schrieb Jaydeep Das: >>> How about modifying the number match regex to: >>> >>> `[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*[^a-zA-Z]` ? >>> >>> The `[^a-zA-Z]` in the end would make sure to not match >>> the `.F` in `X.Find`. > >> No, you cannot do that, because then in X.u+1 you have three tokens X >> .u+ 1, which you do not want, either. > > If X is an integer here, then No, I mean X literally, i.e., an identifier. > > In C/C++ 2.f is equivalent to 2.000000 > However in Kotlin 2.f is invalid syntax. 2.0f is valid. > > So is implementing a proper regex for invalid syntax really > necessary? No, that's not necessary. It can be assumed that invalid syntax does not occur. For this reason... >> Have a look at the regex in the cpp driver. I think we need something >> like this: >> >> /* integers floatingpoint numbers */ >> "|[0-9][0-9_.]*([Ee][*-]?[0-9]+)?[FfLl]*" ... I propose this loose [0-9_.]* after the first digit, even though it would match "9.8_7._65"; we can assume that this invalid token will not occur. BTW, make that [FfLlUl] near the end. >> /* floatingpoint numbers that begin with a decimal point */ >> "|[.][0-9][0-9_]*([Ee][*-]?[0-9]+)?[FfLl]*" > > >> Drop the second option if numbers such as .5 are invalid syntax in >> Kotlin. > .5 is valid syntax in Kotlin. OK, then we need this second branch, which ensures that there is a digit after the fullstop. -- Hannes
diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt index a71dad2674..4b36d51beb 100644 --- a/Documentation/gitattributes.txt +++ b/Documentation/gitattributes.txt @@ -829,6 +829,8 @@ patterns are available: - `java` suitable for source code in the Java language. +- `kotlin` suitable for source code in the Kotlin language. + - `markdown` suitable for Markdown documents. - `matlab` suitable for source code in the MATLAB and Octave languages. diff --git a/t/t4018/kotlin-class b/t/t4018/kotlin-class new file mode 100644 index 0000000000..bb864f22e6 --- /dev/null +++ b/t/t4018/kotlin-class @@ -0,0 +1,5 @@ +class RIGHT { + //comment + //comment + return ChangeMe +} diff --git a/t/t4018/kotlin-enum-class b/t/t4018/kotlin-enum-class new file mode 100644 index 0000000000..8885f908fd --- /dev/null +++ b/t/t4018/kotlin-enum-class @@ -0,0 +1,5 @@ +enum class RIGHT{ + // Left + // a comment + ChangeMe +} diff --git a/t/t4018/kotlin-fun b/t/t4018/kotlin-fun new file mode 100644 index 0000000000..2a60280256 --- /dev/null +++ b/t/t4018/kotlin-fun @@ -0,0 +1,5 @@ +fun RIGHT(){ + //a comment + //b comment + return ChangeMe() +} diff --git a/t/t4018/kotlin-inheritace-class b/t/t4018/kotlin-inheritace-class new file mode 100644 index 0000000000..77376c1f05 --- /dev/null +++ b/t/t4018/kotlin-inheritace-class @@ -0,0 +1,5 @@ +open class RIGHT{ + // a comment + // b comment + // ChangeMe +} diff --git a/t/t4018/kotlin-inline-class b/t/t4018/kotlin-inline-class new file mode 100644 index 0000000000..7bf46dd8d4 --- /dev/null +++ b/t/t4018/kotlin-inline-class @@ -0,0 +1,5 @@ +value class RIGHT(Args){ + // a comment + // b comment + ChangeMe +} diff --git a/t/t4018/kotlin-interface b/t/t4018/kotlin-interface new file mode 100644 index 0000000000..f686ba7770 --- /dev/null +++ b/t/t4018/kotlin-interface @@ -0,0 +1,5 @@ +interface RIGHT{ + //another comment + //another comment + //ChangeMe +} diff --git a/t/t4018/kotlin-nested-fun b/t/t4018/kotlin-nested-fun new file mode 100644 index 0000000000..12186858cb --- /dev/null +++ b/t/t4018/kotlin-nested-fun @@ -0,0 +1,9 @@ +class LEFT{ + class CENTER{ + fun RIGHT( a:Int){ + //comment + //comment + ChangeMe + } + } +} diff --git a/t/t4018/kotlin-public-class b/t/t4018/kotlin-public-class new file mode 100644 index 0000000000..9433fcc226 --- /dev/null +++ b/t/t4018/kotlin-public-class @@ -0,0 +1,5 @@ +public class RIGHT{ + //comment1 + //comment2 + ChangeMe +} diff --git a/t/t4018/kotlin-sealed-class b/t/t4018/kotlin-sealed-class new file mode 100644 index 0000000000..0efa4a4eaf --- /dev/null +++ b/t/t4018/kotlin-sealed-class @@ -0,0 +1,5 @@ +sealed class RIGHT { + // a comment + // b comment + ChangeMe +} diff --git a/t/t4034-diff-words.sh b/t/t4034-diff-words.sh index d5abcf4b4c..15764ee9ac 100755 --- a/t/t4034-diff-words.sh +++ b/t/t4034-diff-words.sh @@ -324,6 +324,7 @@ test_language_driver dts test_language_driver fortran test_language_driver html test_language_driver java +test_language_driver kotlin test_language_driver matlab test_language_driver objc test_language_driver pascal diff --git a/t/t4034/kotlin/expect b/t/t4034/kotlin/expect new file mode 100644 index 0000000000..7062b67319 --- /dev/null +++ b/t/t4034/kotlin/expect @@ -0,0 +1,34 @@ +<BOLD>diff --git a/pre b/post<RESET> +<BOLD>index 3cfa271..20d26cc 100644<RESET> +<BOLD>--- a/pre<RESET> +<BOLD>+++ b/post<RESET> +<CYAN>@@ -1,21 +1,21 @@<RESET> +println("Hello World<RED>!\n<RESET><GREEN>?<RESET>") +<GREEN>(<RESET>1<GREEN>) (<RESET>-1e10<GREEN>) (<RESET>0xabcdef<GREEN>)<RESET> '<RED>x<RESET><GREEN>y<RESET>' +[<RED>a<RESET><GREEN>x<RESET>] <RED>a<RESET><GREEN>x<RESET>-><RED>b a<RESET><GREEN>y x<RESET>.<RED>b<RESET><GREEN>y<RESET> +!<RED>a a<RESET><GREEN>x x<RESET>.inv() <RED>a<RESET><GREEN>x<RESET>*<RED>b a<RESET><GREEN>y x<RESET>&<RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET>*<RED>b a<RESET><GREEN>y x<RESET>/<RED>b a<RESET><GREEN>y x<RESET>%<RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET>+<RED>b a<RESET><GREEN>y x<RESET>-<RED>b<RESET><GREEN>y<RESET> +a <RED>shr<RESET><GREEN>shl<RESET> b +<RED>a<RESET><GREEN>x<RESET><<RED>b a<RESET><GREEN>y x<RESET><=<RED>b a<RESET><GREEN>y x<RESET>><RED>b a<RESET><GREEN>y x<RESET>>=<RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET>==<RED>b a<RESET><GREEN>y x<RESET>!=<RED>b a<RESET><GREEN>y x<RESET>===<RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET> and <RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET>^<RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET> or <RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET>&&<RED>b a<RESET><GREEN>y x<RESET>||<RED>b<RESET> +<RED>a<RESET><GREEN>y<RESET> +<GREEN>x<RESET>=<RED>b a<RESET><GREEN>y x<RESET>+=<RED>b a<RESET><GREEN>y x<RESET>-=<RED>b a<RESET><GREEN>y x<RESET>*=<RED>b a<RESET><GREEN>y x<RESET>/=<RED>b a<RESET><GREEN>y x<RESET>%=<RED>b a<RESET><GREEN>y x<RESET><<=<RED>b a<RESET><GREEN>y x<RESET>>>=<RED>b a<RESET><GREEN>y x<RESET>&=<RED>b a<RESET><GREEN>y x<RESET>^=<RED>b a<RESET><GREEN>y x<RESET>|=<RED>b<RESET><GREEN>y<RESET> +a<RED>=<RESET><GREEN>+=<RESET>b c<RED>+=<RESET><GREEN>=<RESET>d e<RED>-=<RESET><GREEN><=<RESET>f g<RED>*=<RESET><GREEN>>=<RESET>h i<RED>/=<RESET><GREEN>/<RESET>j k<RED>%=<RESET><GREEN>%<RESET>l m<RED><<=<RESET><GREEN><<<RESET>n o<RED>>>=<RESET><GREEN>>><RESET>p q<RED>&=<RESET><GREEN>&<RESET>r s<RED>^=<RESET><GREEN>^<RESET>t u<RED>|=<RESET><GREEN>|<RESET>v +a<RED><<=<RESET><GREEN><=<RESET>b +a<RED>||<RESET><GREEN>|<RESET>b a<RED>&&<RESET><GREEN>&<RESET>b +<RED>a<RESET><GREEN>x<RESET>,y +--a<RED>==<RESET><GREEN>!=<RESET>--b +a++<RED>==<RESET><GREEN>!=<RESET>++b +<RED>0xFF_EC_DE_5E 0b100_000 100_000<RESET><GREEN>0xFF_E1_DE_5E 0b100_100 200_000<RESET> diff --git a/t/t4034/kotlin/post b/t/t4034/kotlin/post new file mode 100644 index 0000000000..20d26cca5f --- /dev/null +++ b/t/t4034/kotlin/post @@ -0,0 +1,21 @@ +println("Hello World?") +(1) (-1e10) (0xabcdef) 'y' +[x] x->y x.y +!x x.inv() x*y x&y +x*y x/y x%y +x+y x-y +a shl b +x<y x<=y x>y x>=y +x==y x!=y x===y +x and y +x^y +x or y +x&&y x||y +x=y x+=y x-=y x*=y x/=y x%=y x<<=y x>>=y x&=y x^=y x|=y +a+=b c=d e<=f g>=h i/j k%l m<<n o>>p q&r s^t u|v +a<=b +a|b a&b +x,y +--a!=--b +a++!=++b +0xFF_E1_DE_5E 0b100_100 200_000 diff --git a/t/t4034/kotlin/pre b/t/t4034/kotlin/pre new file mode 100644 index 0000000000..3cfa271e37 --- /dev/null +++ b/t/t4034/kotlin/pre @@ -0,0 +1,21 @@ +println("Hello World!\n") +1 -1e10 0xabcdef 'x' +[a] a->b a.b +!a a.inv() a*b a&b +a*b a/b a%b +a+b a-b +a shr b +a<b a<=b a>b a>=b +a==b a!=b a===b +a and b +a^b +a or b +a&&b a||b +a=b a+=b a-=b a*=b a/=b a%=b a<<=b a>>=b a&=b a^=b a|=b +a=b c+=d e-=f g*=h i/=j k%=l m<<=n o>>=p q&=r s^=t u|=v +a<<=b +a||b a&&b +a,y +--a==--b +a++==++b +0xFF_EC_DE_5E 0b100_000 100_000 diff --git a/userdiff.c b/userdiff.c index 8578cb0d12..bb701100c6 100644 --- a/userdiff.c +++ b/userdiff.c @@ -168,6 +168,16 @@ PATTERNS("java", "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?" "|[-+*/<>%&^|=!]=" "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"), +PATTERNS("kotlin", + "^[ \t]*(([a-z]+[ \t]+)*(fun|class|interface)[ \t]+.*)$", + /* -- */ + "[_]?[a-zA-Z][a-zA-Z0-9_]*" + /* hexadecimal and binary numbers */ + "|0[xXbB][0-9a-fA-F_]+[lLuU]*" + /* integers and floats */ + "|[0-9._]+([Ee][-+]?[0-9]+)?[fFlLuU]*" + /* unary and binary operators */ + "|[-+*/<>%&^|=!]?=(=)?|--|\\+\\+|<<?=?|>>?=?|&&?|[|]?\\||\\|->\\*?|\\.\\*"), PATTERNS("markdown", "^ {0,3}#{1,6}[ \t].*", /* -- */
The xfuncname pattern finds func/class declarations in diffs to display as a hunk header. The word_regex pattern finds individual tokens in Kotlin code to generate appropriate diffs. This patch adds xfuncname regex and word_regex for Kotlin language. Signed-off-by: Jaydeep P Das <jaydeepjd.8914@gmail.com> --- Documentation/gitattributes.txt | 2 ++ t/t4018/kotlin-class | 5 +++++ t/t4018/kotlin-enum-class | 5 +++++ t/t4018/kotlin-fun | 5 +++++ t/t4018/kotlin-inheritace-class | 5 +++++ t/t4018/kotlin-inline-class | 5 +++++ t/t4018/kotlin-interface | 5 +++++ t/t4018/kotlin-nested-fun | 9 +++++++++ t/t4018/kotlin-public-class | 5 +++++ t/t4018/kotlin-sealed-class | 5 +++++ t/t4034-diff-words.sh | 1 + t/t4034/kotlin/expect | 34 +++++++++++++++++++++++++++++++++ t/t4034/kotlin/post | 21 ++++++++++++++++++++ t/t4034/kotlin/pre | 21 ++++++++++++++++++++ userdiff.c | 10 ++++++++++ 15 files changed, 138 insertions(+) create mode 100644 t/t4018/kotlin-class create mode 100644 t/t4018/kotlin-enum-class create mode 100644 t/t4018/kotlin-fun create mode 100644 t/t4018/kotlin-inheritace-class create mode 100644 t/t4018/kotlin-inline-class create mode 100644 t/t4018/kotlin-interface create mode 100644 t/t4018/kotlin-nested-fun create mode 100644 t/t4018/kotlin-public-class create mode 100644 t/t4018/kotlin-sealed-class create mode 100644 t/t4034/kotlin/expect create mode 100644 t/t4034/kotlin/post create mode 100644 t/t4034/kotlin/pre