The diagnostics routines for SARIF output need to read the source code back
in, so that they can generate "snippet" and "content" records, so they need to
be able to cope with generated data locations. Add support for that in
diagnostic-format-sarif.cc.
gcc/ChangeLog:
* diagnostic-format-sarif.cc (class sarif_builder): Adapt interface
to support generated data locations.
(sarif_builder::maybe_make_physical_location_object): Change the
m_filenames hash_set to support generated data.
(sarif_builder::make_artifact_location_object): Use a source_id rather
than a plain file name.
(sarif_builder::maybe_make_region_object): Adapt to
expanded_location interface changes.
(sarif_builder::maybe_make_region_object_for_context): Likewise.
(sarif_builder::make_artifact_object): Likewise.
(sarif_builder::make_run_object): Handle generated data.
(sarif_builder::maybe_make_artifact_content_object): Likewise.
(get_source_lines): Likewise.
gcc/testsuite/ChangeLog:
* c-c++-common/diagnostic-format-sarif-file-5.c: New test.
---
gcc/diagnostic-format-sarif.cc | 88 +++++++++++--------
.../diagnostic-format-sarif-file-5.c | 31 +++++++
2 files changed, 82 insertions(+), 37 deletions(-)
create mode 100644 gcc/testsuite/c-c++-common/diagnostic-format-sarif-file-5.c
diff --git a/gcc/diagnostic-format-sarif.cc b/gcc/diagnostic-format-sarif.cc
index 1eff71962d7..c7c0e5d4b0a 100644
--- a/gcc/diagnostic-format-sarif.cc
+++ b/gcc/diagnostic-format-sarif.cc
@@ -174,7 +174,7 @@ private:
json::array *maybe_make_kinds_array (diagnostic_event::meaning m) const;
json::object *maybe_make_physical_location_object (location_t loc);
json::object *make_artifact_location_object (location_t loc);
- json::object *make_artifact_location_object (const char *filename);
+ json::object *make_artifact_location_object (source_id src);
json::object *make_artifact_location_object_for_pwd () const;
json::object *maybe_make_region_object (location_t loc) const;
json::object *maybe_make_region_object_for_context (location_t loc) const;
@@ -197,9 +197,9 @@ private:
json::object *make_reporting_descriptor_object_for_cwe_id (int cwe_id) const;
json::object *
make_reporting_descriptor_reference_object_for_cwe_id (int cwe_id);
- json::object *make_artifact_object (const char *filename);
- json::object *maybe_make_artifact_content_object (const char *filename)
const;
- json::object *maybe_make_artifact_content_object (const char *filename,
+ json::object *make_artifact_object (source_id src);
+ json::object *maybe_make_artifact_content_object (source_id src) const;
+ json::object *maybe_make_artifact_content_object (source_id src,
int start_line,
int end_line) const;
json::object *make_fix_object (const rich_location &rich_loc);
@@ -220,7 +220,11 @@ private:
diagnostic group. */
sarif_result *m_cur_group_result;
- hash_set <const char *> m_filenames;
+ /* If the second member is >0, then this is a buffer of generated content,
+ with that length, not a filename. */
+ hash_set <pair_hash <nofree_ptr_hash <const char>,
+ int_hash <unsigned int, -1U> >
+ > m_filenames;
bool m_seen_any_relative_paths;
hash_set <free_string_hash> m_rule_id_set;
json::array *m_rules_arr;
@@ -787,7 +791,8 @@ sarif_builder::maybe_make_physical_location_object
(location_t loc)
/* "artifactLocation" property (SARIF v2.1.0 section 3.29.3). */
json::object *artifact_loc_obj = make_artifact_location_object (loc);
phys_loc_obj->set ("artifactLocation", artifact_loc_obj);
- m_filenames.add (LOCATION_FILE (loc));
+ const auto src = LOCATION_SRC (loc);
+ m_filenames.add ({src.get_filename_or_buffer (), src.get_buffer_len ()});
/* "region" property (SARIF v2.1.0 section 3.29.4). */
if (json::object *region_obj = maybe_make_region_object (loc))
@@ -811,7 +816,7 @@ sarif_builder::maybe_make_physical_location_object
(location_t loc)
json::object *
sarif_builder::make_artifact_location_object (location_t loc)
{
- return make_artifact_location_object (LOCATION_FILE (loc));
+ return make_artifact_location_object (LOCATION_SRC (loc));
}
/* The ID value for use in "uriBaseId" properties (SARIF v2.1.0 section 3.4.4)
@@ -823,10 +828,13 @@ sarif_builder::make_artifact_location_object (location_t
loc)
or return NULL. */
json::object *
-sarif_builder::make_artifact_location_object (const char *filename)
+sarif_builder::make_artifact_location_object (source_id src)
{
json::object *artifact_loc_obj = new json::object ();
+ const auto filename = src.is_buffer ()
+ ? special_fname_generated () : src.get_filename_or_buffer ();
+
/* "uri" property (SARIF v2.1.0 section 3.4.3). */
artifact_loc_obj->set ("uri", new json::string (filename));
@@ -912,9 +920,9 @@ sarif_builder::maybe_make_region_object (location_t loc)
const
expanded_location exploc_start = expand_location (start_loc);
expanded_location exploc_finish = expand_location (finish_loc);
- if (exploc_start.file !=exploc_caret.file)
+ if (exploc_start.src != exploc_caret.src)
return NULL;
- if (exploc_finish.file !=exploc_caret.file)
+ if (exploc_finish.src != exploc_caret.src)
return NULL;
json::object *region_obj = new json::object ();
@@ -963,9 +971,9 @@ sarif_builder::maybe_make_region_object_for_context
(location_t loc) const
expanded_location exploc_start = expand_location (start_loc);
expanded_location exploc_finish = expand_location (finish_loc);
- if (exploc_start.file !=exploc_caret.file)
+ if (exploc_start.src != exploc_caret.src)
return NULL;
- if (exploc_finish.file !=exploc_caret.file)
+ if (exploc_finish.src != exploc_caret.src)
return NULL;
json::object *region_obj = new json::object ();
@@ -979,9 +987,9 @@ sarif_builder::maybe_make_region_object_for_context
(location_t loc) const
/* "snippet" property (SARIF v2.1.0 section 3.30.13). */
if (json::object *artifact_content_obj
- = maybe_make_artifact_content_object (exploc_start.file,
- exploc_start.line,
- exploc_finish.line))
+ = maybe_make_artifact_content_object (exploc_start.src,
+ exploc_start.line,
+ exploc_finish.line))
region_obj->set ("snippet", artifact_content_obj);
return region_obj;
@@ -1298,7 +1306,10 @@ sarif_builder::make_run_object (sarif_invocation
*invocation_obj,
json::array *artifacts_arr = new json::array ();
for (auto iter : m_filenames)
{
- json::object *artifact_obj = make_artifact_object (iter);
+ const auto src = iter.second
+ ? source_id {iter.first, iter.second} /* Memory buffer. */
+ : source_id {iter.first}; /* Filename. */
+ json::object *artifact_obj = make_artifact_object (src);
artifacts_arr->append (artifact_obj);
}
run_obj->set ("artifacts", artifacts_arr);
@@ -1472,37 +1483,37 @@ sarif_builder::maybe_make_cwe_taxonomy_object () const
/* Make an artifact object (SARIF v2.1.0 section 3.24). */
json::object *
-sarif_builder::make_artifact_object (const char *filename)
+sarif_builder::make_artifact_object (source_id src)
{
json::object *artifact_obj = new json::object ();
/* "location" property (SARIF v2.1.0 section 3.24.2). */
- json::object *artifact_loc_obj = make_artifact_location_object (filename);
+ json::object *artifact_loc_obj = make_artifact_location_object (src);
artifact_obj->set ("location", artifact_loc_obj);
/* "contents" property (SARIF v2.1.0 section 3.24.8). */
if (json::object *artifact_content_obj
- = maybe_make_artifact_content_object (filename))
+ = maybe_make_artifact_content_object (src))
artifact_obj->set ("contents", artifact_content_obj);
/* "sourceLanguage" property (SARIF v2.1.0 section 3.24.10). */
if (m_context->m_client_data_hooks)
if (const char *source_lang
= m_context->m_client_data_hooks->maybe_get_sarif_source_language
- (filename))
+ (src.get_filename_or_buffer ()))
artifact_obj->set ("sourceLanguage", new json::string (source_lang));
return artifact_obj;
}
/* Make an artifactContent object (SARIF v2.1.0 section 3.3) for the
- full contents of FILENAME. */
+ full contents of SRC. */
json::object *
-sarif_builder::maybe_make_artifact_content_object (const char *filename) const
+sarif_builder::maybe_make_artifact_content_object (source_id src) const
{
/* Let input.cc handle any charset conversion. */
- char_span utf8_content = get_source_file_content (filename);
+ char_span utf8_content = get_source_file_content (src);
if (!utf8_content)
return NULL;
@@ -1518,10 +1529,12 @@ sarif_builder::maybe_make_artifact_content_object
(const char *filename) const
}
/* Attempt to read the given range of lines from FILENAME; return
- a freshly-allocated 0-terminated buffer containing them, or NULL. */
+ a freshly-allocated buffer containing them, or NULL.
+ The buffer is null-terminated, but could also contain embedded null
+ bytes, so the char_span's length() accessor should be used. */
-static char *
-get_source_lines (const char *filename,
+static char_span
+get_source_lines (source_id src,
int start_line,
int end_line)
{
@@ -1529,9 +1542,9 @@ get_source_lines (const char *filename,
for (int line = start_line; line <= end_line; line++)
{
- char_span line_content = location_get_source_line (filename, line);
+ char_span line_content = location_get_source_line (src, line);
if (!line_content.get_buffer ())
- return NULL;
+ return char_span (nullptr, 0);
result.reserve (line_content.length () + 1);
for (size_t i = 0; i < line_content.length (); i++)
result.quick_push (line_content[i]);
@@ -1539,33 +1552,34 @@ get_source_lines (const char *filename,
}
result.safe_push ('\0');
- return xstrdup (result.address ());
+ return char_span (xstrdup (result.address ()), result.length () - 1);
}
/* Make an artifactContent object (SARIF v2.1.0 section 3.3) for the given
- run of lines within FILENAME (including the endpoints). */
+ run of lines in the source code identified by SRC (including the
+ endpoints). */
json::object *
-sarif_builder::maybe_make_artifact_content_object (const char *filename,
+sarif_builder::maybe_make_artifact_content_object (source_id src,
int start_line,
int end_line) const
{
- char *text_utf8 = get_source_lines (filename, start_line, end_line);
+ const char_span text_utf8 = get_source_lines (src, start_line, end_line);
if (!text_utf8)
return NULL;
/* Don't add it if it's not valid UTF-8. */
- if (!cpp_valid_utf8_p(text_utf8, strlen(text_utf8)))
+ if (!cpp_valid_utf8_p (text_utf8.get_buffer (), text_utf8.length ()))
{
- free (text_utf8);
+ free (const_cast<char *> (text_utf8.get_buffer ()));
return NULL;
}
json::object *artifact_content_obj = new json::object ();
- artifact_content_obj->set ("text", new json::string (text_utf8));
- free (text_utf8);
-
+ artifact_content_obj->set ("text", new json::string (text_utf8.get_buffer (),
+ text_utf8.length ()));
+ free (const_cast<char *> (text_utf8.get_buffer ()));
return artifact_content_obj;
}
diff --git a/gcc/testsuite/c-c++-common/diagnostic-format-sarif-file-5.c
b/gcc/testsuite/c-c++-common/diagnostic-format-sarif-file-5.c
new file mode 100644
index 00000000000..2ca6a069d3f
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/diagnostic-format-sarif-file-5.c
@@ -0,0 +1,31 @@
+/* The goal is to test SARIF output of generated data, such as a _Pragma
string.
+ But SARIF output as of yet does not output macro definitions, so such
+ generated data buffers never end up in the typical SARIF output. One way we
+ can achieve it is to use -fdump-internal-locations, which outputs top-level
+ diagnostic notes inside macro definitions, that SARIF will end up
processing.
+ It also outputs a lot of other stuff to stderr (not to the SARIF file) that
+ is not relevant to this test, so we use a blanket dg-regexp to filter all of
+ that away. */
+
+/* { dg-do compile } */
+/* { dg-options "-fdiagnostics-format=sarif-file -fdump-internal-locations" }
*/
+/* { dg-allow-blank-lines-in-output "" } */
+
+_Pragma("GCC diagnostic push")
+
+/* { dg-regexp {(.|[\n\r])*} } */
+
+/* Because of the way -fdump-internal-locations works, these regexes themselves
+ will end up in the sarif output also. But due to the escaping, they don't
+ match themselves, so they still test what we need. */
+
+/* Four of this pair are output for the tokens inside the
+ _Pragma string (3 plus a PRAGMA_EOL). */
+
+/* { dg-final { scan-sarif-file "\"artifactLocation\": \{\"uri\":
\"<generated>\"," } } */
+/* { dg-final { scan-sarif-file "\"snippet\": \{\"text\": \"GCC diagnostic
push\\\\n\"" } } */
+
+/* One of this pair is output for the overall internal location. */
+
+/* { dg-final { scan-sarif-file "\{\"location\": \{\"uri\": \"<generated>\","
} } */
+/* { dg-final { scan-sarif-file "\"contents\": \{\"text\": \"GCC diagnostic
push\\\\n\\\\0" } } */
