[v3] libcpp: add function to check XID properties
Checks
Commit Message
From: Raiki Tamura <tamaron1203@gmail.com>
Fixed to include the enum's name which I had forgotten to commit.
Thanks
----
This commit adds a new function intended for checking the XID properties
of a possibly unicode character, as well as the accompanying enum
describing the possible properties.
libcpp/ChangeLog:
* charset.cc (cpp_check_xid_property): New.
* include/cpplib.h
(cpp_check_xid_property): New.
(enum cpp_xid_property): New.
Signed-off-by: Raiki Tamura <tamaron1203@gmail.com>
---
libcpp/charset.cc | 36 ++++++++++++++++++++++++++++++++++++
libcpp/include/cpplib.h | 7 +++++++
2 files changed, 43 insertions(+)
Comments
Ping?
Best,
Arthur
On 9/8/23 16:59, Arthur Cohen wrote:
> From: Raiki Tamura <tamaron1203@gmail.com>
>
> Fixed to include the enum's name which I had forgotten to commit.
>
> Thanks
>
> ----
>
> This commit adds a new function intended for checking the XID properties
> of a possibly unicode character, as well as the accompanying enum
> describing the possible properties.
>
> libcpp/ChangeLog:
>
> * charset.cc (cpp_check_xid_property): New.
> * include/cpplib.h
> (cpp_check_xid_property): New.
> (enum cpp_xid_property): New.
>
> Signed-off-by: Raiki Tamura <tamaron1203@gmail.com>
> ---
> libcpp/charset.cc | 36 ++++++++++++++++++++++++++++++++++++
> libcpp/include/cpplib.h | 7 +++++++
> 2 files changed, 43 insertions(+)
>
> diff --git a/libcpp/charset.cc b/libcpp/charset.cc
> index 7b625c9956a..a92ba75539e 100644
> --- a/libcpp/charset.cc
> +++ b/libcpp/charset.cc
> @@ -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
> +cpp_check_xid_property (cppchar_t c)
> +{
> + // fast path for ASCII
> + if (c < 0x80)
> + {
> + if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z'))
> + return CPP_XID_START | CPP_XID_CONTINUE;
> + if (('0' <= c && c <= '9') || c == '_')
> + return CPP_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 CPP_XID_START | CPP_XID_CONTINUE;
> + if (flags & NXX23)
> + return CPP_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
> diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
> index fcdaf082b09..583e3071e90 100644
> --- 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 cpp_xid_property {
> + CPP_XID_START = 1,
> + CPP_XID_CONTINUE = 2
> +};
> +
> +unsigned int cpp_check_xid_property (cppchar_t c);
> +
> #endif /* ! LIBCPP_CPPLIB_H */
On Fri, 8 Sep 2023, Arthur Cohen wrote:
> + if (c < 0x80)
> + {
> + if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z'))
> + return CPP_XID_START | CPP_XID_CONTINUE;
> + if (('0' <= c && c <= '9') || c == '_')
> + return CPP_XID_CONTINUE;
This may be an artifact of how the patch was mailed, but indentation seems
off here (should be six spaces for both return statements).
> + md = (mn + mx) / 2;
> + if (c <= ucnranges[md].end)
> + mx = md;
> + else
> + mn = md + 1;
And likewise here (should be a tab for both assignments).
OK with those indentation fixes.
Hi Joseph,
Thanks for the review!
On 12/18/23 20:00, Joseph Myers wrote:
> On Fri, 8 Sep 2023, Arthur Cohen wrote:
>
>> + if (c < 0x80)
>> + {
>> + if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z'))
>> + return CPP_XID_START | CPP_XID_CONTINUE;
>> + if (('0' <= c && c <= '9') || c == '_')
>> + return CPP_XID_CONTINUE;
>
> This may be an artifact of how the patch was mailed, but indentation seems
> off here (should be six spaces for both return statements) >
>> + md = (mn + mx) / 2;
>> + if (c <= ucnranges[md].end)
>> + mx = md;
>> + else
>> + mn = md + 1;
>
> And likewise here (should be a tab for both assignments).
>
> OK with those indentation fixes.
>
Thanks for noticing - this was indeed misindented.
I'll make the suggested fixes and will push the patch.
Best,
Arthur
@@ -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
+cpp_check_xid_property (cppchar_t c)
+{
+ // fast path for ASCII
+ if (c < 0x80)
+ {
+ if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z'))
+ return CPP_XID_START | CPP_XID_CONTINUE;
+ if (('0' <= c && c <= '9') || c == '_')
+ return CPP_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 CPP_XID_START | CPP_XID_CONTINUE;
+ if (flags & NXX23)
+ return CPP_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 cpp_xid_property {
+ CPP_XID_START = 1,
+ CPP_XID_CONTINUE = 2
+};
+
+unsigned int cpp_check_xid_property (cppchar_t c);
+
#endif /* ! LIBCPP_CPPLIB_H */