| # Show that llvm-strings uses the specified encoding. | |
| RUN: echo a > %t | |
| RUN: echo ab >> %t | |
| RUN: echo abc >> %t | |
| RUN: echo abcd >> %t | |
| # UTF-8 encoding of U+00A0 NON-BREAKING SPACE (which we treat as printable) | |
| RUN: echo -e 'bcde\0302\0240' >> %t | |
| # UTF-8 encoding of U+009F APPLICATION PROGRAM COMMAND (non-printable) | |
| RUN: echo -e 'cdef\0302\0240\0302\0237' >> %t | |
| # Check that partial and invalid UTF-8 characters do not interfere with | |
| # preceding and subsequent strings. | |
| RUN: echo -e '\0342defg\0342' >> %t | |
| RUN: echo -e '\0342\0200efgh\0342\0200' >> %t | |
| # Check that long form options work. | |
| RUN: llvm-strings --encoding s %t | FileCheck --check-prefixes CHECK,CHECK-ASCII --strict-whitespace --match-full-lines %s | |
| RUN: llvm-strings --encoding S %t | FileCheck --check-prefixes CHECK,CHECK-LOCALE --strict-whitespace --match-full-lines %s | |
| RUN: llvm-strings --encoding utf8 %t | FileCheck --check-prefixes CHECK,CHECK-UTF8 --strict-whitespace --match-full-lines %s | |
| # Check that short form options work. | |
| RUN: llvm-strings -e s %t | FileCheck --check-prefixes CHECK,CHECK-ASCII --strict-whitespace --match-full-lines %s | |
| RUN: llvm-strings -e S %t | FileCheck --check-prefixes CHECK,CHECK-LOCALE --strict-whitespace --match-full-lines %s | |
| RUN: llvm-strings -e utf8 %t | FileCheck --check-prefixes CHECK,CHECK-UTF8 --strict-whitespace --match-full-lines %s | |
| # Check that the output of no options, -e S, and --encoding S all match. | |
| RUN: llvm-strings -e S %t > %t.1 | |
| RUN: llvm-strings --encoding S %t > %t.2 | |
| RUN: llvm-strings %t > %t.3 | |
| RUN: cmp %t.1 %t.2 | |
| RUN: cmp %t.1 %t.3 | |
| # The first line containing just abcd should always be matched. | |
| CHECK:abcd | |
| # In -e s, non-ASCII bytes should not be included. | |
| CHECK-ASCII:bcde | |
| CHECK-ASCII:cdef | |
| CHECK-ASCII:defg | |
| CHECK-ASCII:efgh | |
| # In -e S, any bytes of U+00A0 and U+009F may or may not be included depending | |
| # on the locale in effect. The locale in effect may also be altered by llvm-lit. | |
| # Make sure if changing the test that the byte representations should not allow | |
| # this to be split into multiple strings in non-UTF-8 locales. | |
| CHECK-LOCALE:bcde{{(\xc2\xa0?)?}} | |
| CHECK-LOCALE:cdef{{(\xc2(\xa0(\xc2\x9f?)?)?)?}} | |
| CHECK-LOCALE:{{\xe2?}}defg{{\xe2?}} | |
| CHECK-LOCALE:{{(\xe2?\x80)?}}efgh{{(\xe2\x80?)?}} | |
| # In -e utf8, all bytes of U+00A0 should be included, but none of U+009F. The | |
| # partial multibyte characters should not prevent abcd from being detected as a | |
| # string. | |
| CHECK-UTF8:bcde{{\xc2\xa0}} | |
| CHECK-UTF8:cdef{{\xc2\xa0}} | |
| CHECK-UTF8:defg | |
| CHECK-UTF8:efgh | |
| # Check that invalid --encoding values are rejected. | |
| RUN: not llvm-strings --encoding x 2>&1 %t | FileCheck --check-prefix CHECK-ERROR %s | |
| RUN: not llvm-strings -e x 2>&1 %t | FileCheck --check-prefix CHECK-ERROR %s | |
| CHECK-ERROR: error: 'x' is not a valid value for '--encoding=' | |
| # llvm-strings reads the input in chunks of 16384 bytes. Encodings with | |
| # multibyte characters may have characters cross chunk boundaries. The string | |
| # contains a full multibyte character before the boundary, a multibyte | |
| # character that crosses the boundary, and a full multibyte character after the | |
| # boundary. This test has four variants: the minimum length may or may not | |
| # already be reached before the chunk boundary, and the character that crosses | |
| # the boundary may or may not be printable. | |
| # | |
| RUN: printf "%16380s" | tr " " "\0" > %t | |
| # v chunk boundary | |
| RUN: echo -n -e "\0302\0240e\0302\0240e\0302\0240e\0302\0240" >> %t | |
| RUN: llvm-strings -e utf8 %t | \ | |
| RUN: FileCheck %s --check-prefix=CHECK-UTF8-CHUNK-A --match-full-lines --strict-whitespace --implicit-check-not={{.}} | |
| RUN: printf "%16383s" | tr " " "\0" > %t | |
| # v chunk boundary | |
| RUN: echo -n -e "\0302\0240e\0302\0240e\0302\0240e\0302\0240" >> %t | |
| RUN: llvm-strings -e utf8 %t | \ | |
| RUN: FileCheck %s --check-prefix=CHECK-UTF8-CHUNK-A --match-full-lines --strict-whitespace --implicit-check-not={{.}} | |
| CHECK-UTF8-CHUNK-A:{{\xc2\xa0e\xc2\xa0e\xc2\xa0e\xc2\xa0}} | |
| RUN: printf "%16379s" | tr " " "\0" > %t | |
| # v chunk boundary | |
| RUN: echo -n -e "e\0302\0240e\0302\0237e\0302\0240e\0302\0240e" >> %t | |
| RUN: llvm-strings -e utf8 %t | \ | |
| RUN: FileCheck %s --check-prefix=CHECK-UTF8-CHUNK-B --match-full-lines --strict-whitespace --implicit-check-not={{.}} | |
| RUN: printf "%16382s" | tr " " "\0" > %t | |
| # v chunk boundary | |
| RUN: echo -n -e "e\0302\0237e\0302\0240e\0302\0240e\0342" >> %t | |
| RUN: llvm-strings -e utf8 %t | \ | |
| RUN: FileCheck %s --check-prefix=CHECK-UTF8-CHUNK-B --match-full-lines --strict-whitespace --implicit-check-not={{.}} | |
| CHECK-UTF8-CHUNK-B:{{e\xc2\xa0e\xc2\xa0e}} |