libcpp: add function to check XID properties
Checks
Commit Message
From: Raiki Tamura <tamaron1203@gmail.com>
libcpp/ChangeLog:
* charset.cc (check_xid_property):new function to check XID_Start and XID_Continue
* include/cpplib.h (check_xid_property):add enum representing XID properties
Signed-off-by: Raiki Tamura <tamaron1203@gmail.com>
---
libcpp/charset.cc | 36 ++++++++++++++++++++++++++++++++++++
libcpp/include/cpplib.h | 7 +++++++
2 files changed, 43 insertions(+)
Comments
On Fri, Sep 08, 2023 at 02:58:40PM +0200, Arthur Cohen wrote:
> From: Raiki Tamura <tamaron1203@gmail.com>
>
> libcpp/ChangeLog:
>
> * charset.cc (check_xid_property):new function to check XID_Start and XID_Continue
> * include/cpplib.h (check_xid_property):add enum representing XID properties
Just random comments, not a proper review.
1) functions exported from libcpp should IMNSHO use the cpp_ prefix
2) similarly the enumerators should be prefixed with CPP_
3) formatting of the ChangeLog entry is incorrect. There should be a space
after ): followed by uppercase rather than lowercase letter, descriptions
should end with . and there should be line wrapping so that it fits into 80
columns. For a new function, one can just say New. or New function.,
doesn't need to describe what it is good for. And the include/cpplib.h
changes don't describe what actually changed. A new anonymous enum (why not
a named one?) was added, and check_xid_property declared.
> --- a/libcpp/include/cpplib.h
> +++ b/libcpp/include/cpplib.h
> @@ -1606,4 +1606,11 @@ bool cpp_valid_utf8_p (const char *data, size_t num_bytes);
> bool cpp_is_combining_char (cppchar_t c);
> bool cpp_is_printable_char (cppchar_t c);
>
> +enum {
> + XID_START = 1,
> + XID_CONTINUE = 2
Formatting. There should be indentation just by 2 columns rather than 3.
Jakub
@@ -1256,6 +1256,42 @@ _cpp_uname2c_uax44_lm2 (const char *name, size_t len, char *canon_name)
return result;
}
+/* Returns flags representing the XID properties of the given codepoint. */
+unsigned int
+check_xid_property (cppchar_t c)
+{
+ // fast path for ASCII
+ if (c < 0x80)
+ {
+ if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z'))
+ return XID_START | XID_CONTINUE;
+ if (('0' <= c && c <= '9') || c == '_')
+ return XID_CONTINUE;
+ }
+
+ if (c > UCS_LIMIT)
+ return 0;
+
+ int mn, mx, md;
+ mn = 0;
+ mx = ARRAY_SIZE (ucnranges) - 1;
+ while (mx != mn)
+ {
+ md = (mn + mx) / 2;
+ if (c <= ucnranges[md].end)
+ mx = md;
+ else
+ mn = md + 1;
+ }
+
+ unsigned short flags = ucnranges[mn].flags;
+
+ if (flags & CXX23)
+ return XID_START | XID_CONTINUE;
+ if (flags & NXX23)
+ return XID_CONTINUE;
+ return 0;
+}
/* Returns 1 if C is valid in an identifier, 2 if C is valid except at
the start of an identifier, and 0 if C is not valid in an
@@ -1606,4 +1606,11 @@ bool cpp_valid_utf8_p (const char *data, size_t num_bytes);
bool cpp_is_combining_char (cppchar_t c);
bool cpp_is_printable_char (cppchar_t c);
+enum {
+ XID_START = 1,
+ XID_CONTINUE = 2
+};
+
+unsigned int check_xid_property (cppchar_t c);
+
#endif /* ! LIBCPP_CPPLIB_H */