#include "c-common.h"
#include "c-indentation.h"
#include "selftest.h"
-
-extern cpp_options *cpp_opts;
+#include "diagnostic.h"
/* Round up VIS_COLUMN to nearest tab stop. */
expanded_location next_stmt_exploc = expand_location (next_stmt_loc);
expanded_location guard_exploc = expand_location (guard_loc);
- const unsigned int tab_width = cpp_opts->tabstop;
+ const unsigned int tab_width = global_dc->tabstop;
/* They must be in the same file. */
if (next_stmt_exploc.file != body_exploc.file)
cpp_opts->track_macro_expansion = 2;
break;
- case OPT_ftabstop_:
- /* It is documented that we silently ignore silly values. */
- if (value >= 1 && value <= 100)
- cpp_opts->tabstop = value;
- break;
-
case OPT_fexec_charset_:
cpp_opts->narrow_charset = arg;
break;
EnumValue
Enum(strong_eval_order) String(all) Value(2)
-ftabstop=
-C ObjC C++ ObjC++ Joined RejectNegative UInteger
--ftabstop=<number> Distance between tab stops for column reporting.
-
ftemplate-backtrace-limit=
C++ ObjC++ Joined RejectNegative UInteger Var(template_backtrace_limit) Init(10)
Set the maximum number of template instantiation notes for a single warning or error.
EnumValue
Enum(diagnostic_url_rule) String(auto) Value(DIAGNOSTICS_URL_AUTO)
+fdiagnostics-column-unit=
+Common Joined RejectNegative Enum(diagnostics_column_unit)
+-fdiagnostics-column-unit=[display|byte] Select whether column numbers are output as display columns (default) or raw bytes.
+
+fdiagnostics-column-origin=
+Common Joined RejectNegative UInteger
+-fdiagnostics-column-origin=<number> Set the number of the first column. The default is 1-based as per GNU style, but some utilities may expect 0-based, for example.
+
fdiagnostics-format=
Common Joined RejectNegative Enum(diagnostics_output_format)
-fdiagnostics-format=[text|json] Select output format.
SourceInclude
diagnostic.h
+Enum
+Name(diagnostics_column_unit) Type(int)
+
+EnumValue
+Enum(diagnostics_column_unit) String(display) Value(DIAGNOSTICS_COLUMN_UNIT_DISPLAY)
+
+EnumValue
+Enum(diagnostics_column_unit) String(byte) Value(DIAGNOSTICS_COLUMN_UNIT_BYTE)
+
Enum
Name(diagnostics_output_format) Type(int)
Common Joined RejectNegative Var(flag_diagnostics_path_format) Enum(diagnostic_path_format) Init(DPF_INLINE_EVENTS)
Specify how to print any control-flow path associated with a diagnostic.
+ftabstop=
+Common Joined RejectNegative UInteger
+-ftabstop=<number> Distance between tab stops for column reporting.
+
Enum
Name(diagnostic_path_format) Type(int)
#include "system.h"
#include "coretypes.h"
#include "diagnostic.h"
+#include "selftest-diagnostic.h"
#include "diagnostic-metadata.h"
#include "json.h"
#include "selftest.h"
/* Generate a JSON object for LOC. */
json::value *
-json_from_expanded_location (location_t loc)
+json_from_expanded_location (diagnostic_context *context, location_t loc)
{
expanded_location exploc = expand_location (loc);
json::object *result = new json::object ();
if (exploc.file)
result->set ("file", new json::string (exploc.file));
result->set ("line", new json::integer_number (exploc.line));
- result->set ("column", new json::integer_number (exploc.column));
+
+ const enum diagnostics_column_unit orig_unit = context->column_unit;
+ struct
+ {
+ const char *name;
+ enum diagnostics_column_unit unit;
+ } column_fields[] = {
+ {"display-column", DIAGNOSTICS_COLUMN_UNIT_DISPLAY},
+ {"byte-column", DIAGNOSTICS_COLUMN_UNIT_BYTE}
+ };
+ int the_column = INT_MIN;
+ for (int i = 0; i != sizeof column_fields / sizeof (*column_fields); ++i)
+ {
+ context->column_unit = column_fields[i].unit;
+ const int col = diagnostic_converted_column (context, exploc);
+ result->set (column_fields[i].name, new json::integer_number (col));
+ if (column_fields[i].unit == orig_unit)
+ the_column = col;
+ }
+ gcc_assert (the_column != INT_MIN);
+ result->set ("column", new json::integer_number (the_column));
+ context->column_unit = orig_unit;
return result;
}
/* Generate a JSON object for LOC_RANGE. */
static json::object *
-json_from_location_range (const location_range *loc_range, unsigned range_idx)
+json_from_location_range (diagnostic_context *context,
+ const location_range *loc_range, unsigned range_idx)
{
location_t caret_loc = get_pure_location (loc_range->m_loc);
location_t finish_loc = get_finish (loc_range->m_loc);
json::object *result = new json::object ();
- result->set ("caret", json_from_expanded_location (caret_loc));
+ result->set ("caret", json_from_expanded_location (context, caret_loc));
if (start_loc != caret_loc
&& start_loc != UNKNOWN_LOCATION)
- result->set ("start", json_from_expanded_location (start_loc));
+ result->set ("start", json_from_expanded_location (context, start_loc));
if (finish_loc != caret_loc
&& finish_loc != UNKNOWN_LOCATION)
- result->set ("finish", json_from_expanded_location (finish_loc));
+ result->set ("finish", json_from_expanded_location (context, finish_loc));
if (loc_range->m_label)
{
/* Generate a JSON object for HINT. */
static json::object *
-json_from_fixit_hint (const fixit_hint *hint)
+json_from_fixit_hint (diagnostic_context *context, const fixit_hint *hint)
{
json::object *fixit_obj = new json::object ();
location_t start_loc = hint->get_start_loc ();
- fixit_obj->set ("start", json_from_expanded_location (start_loc));
+ fixit_obj->set ("start", json_from_expanded_location (context, start_loc));
location_t next_loc = hint->get_next_loc ();
- fixit_obj->set ("next", json_from_expanded_location (next_loc));
+ fixit_obj->set ("next", json_from_expanded_location (context, next_loc));
fixit_obj->set ("string", new json::string (hint->get_string ()));
return fixit_obj;
else
{
/* Otherwise, make diag_obj be the top-level object within the group;
- add a "children" array. */
+ add a "children" array and record the column origin. */
toplevel_array->append (diag_obj);
cur_group = diag_obj;
cur_children_array = new json::array ();
diag_obj->set ("children", cur_children_array);
+ diag_obj->set ("column-origin",
+ new json::integer_number (context->column_origin));
}
const rich_location *richloc = diagnostic->richloc;
for (unsigned int i = 0; i < richloc->get_num_locations (); i++)
{
const location_range *loc_range = richloc->get_range (i);
- json::object *loc_obj = json_from_location_range (loc_range, i);
+ json::object *loc_obj = json_from_location_range (context, loc_range, i);
if (loc_obj)
loc_array->append (loc_obj);
}
for (unsigned int i = 0; i < richloc->get_num_fixit_hints (); i++)
{
const fixit_hint *hint = richloc->get_fixit_hint (i);
- json::object *fixit_obj = json_from_fixit_hint (hint);
+ json::object *fixit_obj = json_from_fixit_hint (context, hint);
fixit_array->append (fixit_obj);
}
}
static void
test_unknown_location ()
{
- delete json_from_expanded_location (UNKNOWN_LOCATION);
+ test_diagnostic_context dc;
+ delete json_from_expanded_location (&dc, UNKNOWN_LOCATION);
}
/* Verify that we gracefully handle attempts to serialize bad
loc_range.m_range_display_kind = SHOW_RANGE_WITH_CARET;
loc_range.m_label = NULL;
- json::object *obj = json_from_location_range (&loc_range, 0);
+ test_diagnostic_context dc;
+ json::object *obj = json_from_location_range (&dc, &loc_range, 0);
/* We should have a "caret" value, but no "start" or "finish" values. */
ASSERT_TRUE (obj != NULL);
ASSERT_TRUE (obj->get ("caret") != NULL);
class exploc_with_display_col : public expanded_location
{
public:
- exploc_with_display_col (const expanded_location &exploc)
+ exploc_with_display_col (const expanded_location &exploc, int tabstop)
: expanded_location (exploc),
- m_display_col (location_compute_display_column (exploc)) {}
+ m_display_col (location_compute_display_column (exploc, tabstop))
+ {}
int m_display_col;
};
class layout_point
{
public:
- layout_point (const expanded_location &exploc)
+ layout_point (const exploc_with_display_col &exploc)
: m_line (exploc.line)
{
m_columns[CU_BYTES] = exploc.column;
- m_columns[CU_DISPLAY_COLS] = location_compute_display_column (exploc);
+ m_columns[CU_DISPLAY_COLS] = exploc.m_display_col;
}
linenum_type m_line;
class layout_range
{
public:
- layout_range (const expanded_location *start_exploc,
- const expanded_location *finish_exploc,
+ layout_range (const exploc_with_display_col &start_exploc,
+ const exploc_with_display_col &finish_exploc,
enum range_display_kind range_display_kind,
- const expanded_location *caret_exploc,
+ const exploc_with_display_col &caret_exploc,
unsigned original_idx,
const range_label *label);
/* A struct for use by layout::print_source_line for telling
layout::print_annotation_line the extents of the source line that
- it printed, so that underlines can be clipped appropriately. */
+ it printed, so that underlines can be clipped appropriately. Units
+ are 1-based display columns. */
struct line_bounds
{
- int m_first_non_ws;
- int m_last_non_ws;
+ int m_first_non_ws_disp_col;
+ int m_last_non_ws_disp_col;
- void convert_to_display_cols (char_span line)
+ line_bounds ()
{
- m_first_non_ws = cpp_byte_column_to_display_column (line.get_buffer (),
- line.length (),
- m_first_non_ws);
-
- m_last_non_ws = cpp_byte_column_to_display_column (line.get_buffer (),
- line.length (),
- m_last_non_ws);
+ m_first_non_ws_disp_col = INT_MAX;
+ m_last_non_ws_disp_col = 0;
}
};
private:
bool will_show_line_p (linenum_type row) const;
void print_leading_fixits (linenum_type row);
- void print_source_line (linenum_type row, const char *line, int line_bytes,
- line_bounds *lbounds_out);
+ line_bounds print_source_line (linenum_type row, const char *line,
+ int line_bytes);
bool should_print_annotation_line_p (linenum_type row) const;
void start_annotation_line (char margin_char = ' ') const;
void print_annotation_line (linenum_type row, const line_bounds lbounds);
Initialize various layout_point fields from expanded_location
equivalents; we've already filtered on file. */
-layout_range::layout_range (const expanded_location *start_exploc,
- const expanded_location *finish_exploc,
+layout_range::layout_range (const exploc_with_display_col &start_exploc,
+ const exploc_with_display_col &finish_exploc,
enum range_display_kind range_display_kind,
- const expanded_location *caret_exploc,
+ const exploc_with_display_col &caret_exploc,
unsigned original_idx,
const range_label *label)
-: m_start (*start_exploc),
- m_finish (*finish_exploc),
+: m_start (start_exploc),
+ m_finish (finish_exploc),
m_range_display_kind (range_display_kind),
- m_caret (*caret_exploc),
+ m_caret (caret_exploc),
m_original_idx (original_idx),
m_label (label)
{
#if CHECKING_P
+/* Default for when we don't care what the tab expansion is set to. */
+static const int def_tabstop = 8;
+
/* Create some expanded locations for testing layout_range. The filename
member of the explocs is set to the empty string. This member will only be
inspected by the calls to location_compute_display_column() made from the
= {"", start_line, start_col, NULL, false};
const expanded_location finish_exploc
= {"", end_line, end_col, NULL, false};
- return layout_range (&start_exploc, &finish_exploc, SHOW_RANGE_WITHOUT_CARET,
- &start_exploc, 0, NULL);
+ return layout_range (exploc_with_display_col (start_exploc, def_tabstop),
+ exploc_with_display_col (finish_exploc, def_tabstop),
+ SHOW_RANGE_WITHOUT_CARET,
+ exploc_with_display_col (start_exploc, def_tabstop),
+ 0, NULL);
}
/* Selftests for layout_range::contains_point and
: m_context (context),
m_pp (context->printer),
m_primary_loc (richloc->get_range (0)->m_loc),
- m_exploc (richloc->get_expanded_location (0)),
+ m_exploc (richloc->get_expanded_location (0), context->tabstop),
m_colorizer (context, diagnostic_kind),
m_colorize_source_p (context->colorize_source_p),
m_show_labels_p (context->show_labels_p),
/* Everything is now known to be in the correct source file,
but it may require further sanitization. */
- layout_range ri (&start, &finish, loc_range->m_range_display_kind, &caret,
+ layout_range ri (exploc_with_display_col (start, m_context->tabstop),
+ exploc_with_display_col (finish, m_context->tabstop),
+ loc_range->m_range_display_kind,
+ exploc_with_display_col (caret, m_context->tabstop),
original_idx, loc_range->m_label);
/* If we have a range that finishes before it starts (perhaps
= get_line_bytes_without_trailing_whitespace (line.get_buffer (),
line.length ());
int eol_display_column
- = cpp_display_width (line.get_buffer (), line_bytes);
+ = cpp_display_width (line.get_buffer (), line_bytes, m_context->tabstop);
if (caret_display_column > eol_display_column
|| !caret_display_column)
{
}
/* Print line ROW of source code, potentially colorized at any ranges, and
- populate *LBOUNDS_OUT.
- LINE is the source line (not necessarily 0-terminated) and LINE_BYTES
- is its length in bytes.
- This function deals only with byte offsets, not display columns, so
- m_x_offset_display must be converted from display to byte units. In
- particular, LINE_BYTES and LBOUNDS_OUT are in bytes. */
+ return the line bounds. LINE is the source line (not necessarily
+ 0-terminated) and LINE_BYTES is its length in bytes. In order to handle both
+ colorization and tab expansion, this function tracks the line position in
+ both byte and display column units. */
-void
-layout::print_source_line (linenum_type row, const char *line, int line_bytes,
- line_bounds *lbounds_out)
+line_bounds
+layout::print_source_line (linenum_type row, const char *line, int line_bytes)
{
m_colorizer.set_normal_text ();
else
pp_space (m_pp);
- /* We will stop printing the source line at any trailing whitespace, and start
- printing it as per m_x_offset_display. */
+ /* We will stop printing the source line at any trailing whitespace. */
line_bytes = get_line_bytes_without_trailing_whitespace (line,
line_bytes);
- int x_offset_bytes = 0;
- if (m_x_offset_display)
- {
- x_offset_bytes = cpp_display_column_to_byte_column (line, line_bytes,
- m_x_offset_display);
- /* In case the leading portion of the line that will be skipped over ends
- with a character with wcwidth > 1, then it is possible we skipped too
- much, so account for that by padding with spaces. */
- const int overage
- = cpp_byte_column_to_display_column (line, line_bytes, x_offset_bytes)
- - m_x_offset_display;
- for (int column = 0; column < overage; ++column)
- pp_space (m_pp);
- line += x_offset_bytes;
- }
- /* Print the line. */
- int first_non_ws = INT_MAX;
- int last_non_ws = 0;
- for (int col_byte = 1 + x_offset_bytes; col_byte <= line_bytes; col_byte++)
+ /* This object helps to keep track of which display column we are at, which is
+ necessary for computing the line bounds in display units, for doing
+ tab expansion, and for implementing m_x_offset_display. */
+ cpp_display_width_computation dw (line, line_bytes, m_context->tabstop);
+
+ /* Skip the first m_x_offset_display display columns. In case the leading
+ portion that will be skipped ends with a character with wcwidth > 1, then
+ it is possible we skipped too much, so account for that by padding with
+ spaces. Note that this does the right thing too in case a tab was the last
+ character to be skipped over; the tab is effectively replaced by the
+ correct number of trailing spaces needed to offset by the desired number of
+ display columns. */
+ for (int skipped_display_cols = dw.advance_display_cols (m_x_offset_display);
+ skipped_display_cols > m_x_offset_display; --skipped_display_cols)
+ pp_space (m_pp);
+
+ /* Print the line and compute the line_bounds. */
+ line_bounds lbounds;
+ while (!dw.done ())
{
/* Assuming colorization is enabled for the caret and underline
characters, we may also colorize the associated characters
{
bool in_range_p;
point_state state;
- in_range_p = get_state_at_point (row, col_byte,
+ const int start_byte_col = dw.bytes_processed () + 1;
+ in_range_p = get_state_at_point (row, start_byte_col,
0, INT_MAX,
CU_BYTES,
&state);
else
m_colorizer.set_normal_text ();
}
- char c = *line;
- if (c == '\0' || c == '\t' || c == '\r')
- c = ' ';
- if (c != ' ')
+
+ /* Get the display width of the next character to be output, expanding
+ tabs and replacing some control bytes with spaces as necessary. */
+ const char *c = dw.next_byte ();
+ const int start_disp_col = dw.display_cols_processed () + 1;
+ const int this_display_width = dw.process_next_codepoint ();
+ if (*c == '\t')
+ {
+ /* The returned display width is the number of spaces into which the
+ tab should be expanded. */
+ for (int i = 0; i != this_display_width; ++i)
+ pp_space (m_pp);
+ continue;
+ }
+ if (*c == '\0' || *c == '\r')
{
- last_non_ws = col_byte;
- if (first_non_ws == INT_MAX)
- first_non_ws = col_byte;
+ /* cpp_wcwidth() promises to return 1 for all control bytes, and we
+ want to output these as a single space too, so this case is
+ actually the same as the '\t' case. */
+ gcc_assert (this_display_width == 1);
+ pp_space (m_pp);
+ continue;
}
- pp_character (m_pp, c);
- line++;
+
+ /* We have a (possibly multibyte) character to output; update the line
+ bounds if it is not whitespace. */
+ if (*c != ' ')
+ {
+ lbounds.m_last_non_ws_disp_col = dw.display_cols_processed ();
+ if (lbounds.m_first_non_ws_disp_col == INT_MAX)
+ lbounds.m_first_non_ws_disp_col = start_disp_col;
+ }
+
+ /* Output the character. */
+ while (c != dw.next_byte ()) pp_character (m_pp, *c++);
}
print_newline ();
-
- lbounds_out->m_first_non_ws = first_non_ws;
- lbounds_out->m_last_non_ws = last_non_ws;
+ return lbounds;
}
/* Determine if we should print an annotation line for ROW.
}
/* Print a line consisting of the caret/underlines for the given
- source line. This function works with display columns, rather than byte
- counts; in particular, LBOUNDS should be in display column units. */
+ source line. */
void
layout::print_annotation_line (linenum_type row, const line_bounds lbounds)
{
int x_bound = get_x_bound_for_row (row, m_exploc.m_display_col,
- lbounds.m_last_non_ws);
+ lbounds.m_last_non_ws_disp_col);
start_annotation_line ();
pp_space (m_pp);
bool in_range_p;
point_state state;
in_range_p = get_state_at_point (row, column,
- lbounds.m_first_non_ws,
- lbounds.m_last_non_ws,
+ lbounds.m_first_non_ws_disp_col,
+ lbounds.m_last_non_ws_disp_col,
CU_DISPLAY_COLS,
&state);
if (in_range_p)
class line_label
{
public:
- line_label (int state_idx, int column, label_text text)
+ line_label (diagnostic_context *context, int state_idx, int column,
+ label_text text)
: m_state_idx (state_idx), m_column (column),
m_text (text), m_label_line (0), m_has_vbar (true)
{
const int bytes = strlen (text.m_buffer);
- m_display_width = cpp_display_width (text.m_buffer, bytes);
+ m_display_width
+ = cpp_display_width (text.m_buffer, bytes, context->tabstop);
}
/* Sorting is primarily by column, then by state index. */
if (text.m_buffer == NULL)
continue;
- labels.safe_push (line_label (i, disp_col, text));
+ labels.safe_push (line_label (m_context, i, disp_col, text));
}
}
/* Get the range of bytes or display columns that HINT would affect. */
static column_range
-get_affected_range (const fixit_hint *hint, enum column_unit col_unit)
+get_affected_range (diagnostic_context *context,
+ const fixit_hint *hint, enum column_unit col_unit)
{
expanded_location exploc_start = expand_location (hint->get_start_loc ());
expanded_location exploc_finish = expand_location (hint->get_next_loc ());
int finish_column;
if (col_unit == CU_DISPLAY_COLS)
{
- start_column = location_compute_display_column (exploc_start);
+ start_column
+ = location_compute_display_column (exploc_start, context->tabstop);
if (hint->insertion_p ())
finish_column = start_column - 1;
else
- finish_column = location_compute_display_column (exploc_finish);
+ finish_column
+ = location_compute_display_column (exploc_finish, context->tabstop);
}
else
{
/* Get the range of display columns that would be printed for HINT. */
static column_range
-get_printed_columns (const fixit_hint *hint)
+get_printed_columns (diagnostic_context *context, const fixit_hint *hint)
{
expanded_location exploc = expand_location (hint->get_start_loc ());
- int start_column = location_compute_display_column (exploc);
- int hint_width = cpp_display_width (hint->get_string (),
- hint->get_length ());
+ int start_column = location_compute_display_column (exploc, context->tabstop);
+ int hint_width = cpp_display_width (hint->get_string (), hint->get_length (),
+ context->tabstop);
int final_hint_column = start_column + hint_width - 1;
if (hint->insertion_p ())
{
{
exploc = expand_location (hint->get_next_loc ());
--exploc.column;
- int finish_column = location_compute_display_column (exploc);
+ int finish_column
+ = location_compute_display_column (exploc, context->tabstop);
return column_range (start_column,
MAX (finish_column, final_hint_column));
}
correction (column_range affected_bytes,
column_range affected_columns,
column_range printed_columns,
- const char *new_text, size_t new_text_len)
+ const char *new_text, size_t new_text_len,
+ int tabstop)
: m_affected_bytes (affected_bytes),
m_affected_columns (affected_columns),
m_printed_columns (printed_columns),
m_text (xstrdup (new_text)),
m_byte_length (new_text_len),
+ m_tabstop (tabstop),
m_alloc_sz (new_text_len + 1)
{
compute_display_cols ();
void compute_display_cols ()
{
- m_display_cols = cpp_display_width (m_text, m_byte_length);
+ m_display_cols = cpp_display_width (m_text, m_byte_length, m_tabstop);
}
void overwrite (int dst_offset, const char_span &src_span)
char *m_text;
size_t m_byte_length; /* Not including null-terminator. */
int m_display_cols;
+ int m_tabstop;
size_t m_alloc_sz;
};
class line_corrections
{
public:
- line_corrections (const char *filename, linenum_type row)
- : m_filename (filename), m_row (row)
+ line_corrections (diagnostic_context *context, const char *filename,
+ linenum_type row)
+ : m_context (context), m_filename (filename), m_row (row)
{}
~line_corrections ();
void add_hint (const fixit_hint *hint);
+ diagnostic_context *m_context;
const char *m_filename;
linenum_type m_row;
auto_vec <correction *> m_corrections;
void
line_corrections::add_hint (const fixit_hint *hint)
{
- column_range affected_bytes = get_affected_range (hint, CU_BYTES);
- column_range affected_columns = get_affected_range (hint, CU_DISPLAY_COLS);
- column_range printed_columns = get_printed_columns (hint);
+ column_range affected_bytes = get_affected_range (m_context, hint, CU_BYTES);
+ column_range affected_columns = get_affected_range (m_context, hint,
+ CU_DISPLAY_COLS);
+ column_range printed_columns = get_printed_columns (m_context, hint);
/* Potentially consolidate. */
if (!m_corrections.is_empty ())
affected_columns,
printed_columns,
hint->get_string (),
- hint->get_length ()));
+ hint->get_length (),
+ m_context->tabstop));
}
/* If there are any fixit hints on source line ROW, print them.
{
/* Build a list of correction instances for the line,
potentially consolidating hints (for the sake of readability). */
- line_corrections corrections (m_exploc.file, row);
+ line_corrections corrections (m_context, m_exploc.file, row);
for (unsigned int i = 0; i < m_fixit_hints.length (); i++)
{
const fixit_hint *hint = m_fixit_hints[i];
if (!line)
return;
- line_bounds lbounds;
print_leading_fixits (row);
- print_source_line (row, line.get_buffer (), line.length (), &lbounds);
+ const line_bounds lbounds
+ = print_source_line (row, line.get_buffer (), line.length ());
if (should_print_annotation_line_p (row))
- {
- if (lbounds.m_first_non_ws != INT_MAX)
- lbounds.convert_to_display_cols (line);
- print_annotation_line (row, lbounds);
- }
+ print_annotation_line (row, lbounds);
if (m_show_labels_p)
print_any_labels (row);
print_trailing_fixits (row);
char_span lspan = location_get_source_line (tmp.get_filename (), 1);
ASSERT_EQ (line_display_cols,
- cpp_display_width (lspan.get_buffer (), lspan.length ()));
+ cpp_display_width (lspan.get_buffer (), lspan.length (),
+ def_tabstop));
ASSERT_EQ (line_display_cols,
- location_compute_display_column (expand_location (line_end)));
+ location_compute_display_column (expand_location (line_end),
+ def_tabstop));
ASSERT_EQ (0, memcmp (lspan.get_buffer () + (emoji_col - 1),
"\xf0\x9f\x98\x82\xf0\x9f\x98\x82", 8));
}
+static void
+test_layout_x_offset_display_tab (const line_table_case &case_)
+{
+ const char *content
+ = "This line is very long, so that we can use it to test the logic for "
+ "clipping long lines. Also this: `\t' is a tab that occupies 1 byte and "
+ "a variable number of display columns, starting at column #103.\n";
+
+ /* Number of bytes in the line, subtracting one to remove the newline. */
+ const int line_bytes = strlen (content) - 1;
+
+ /* The column where the tab begins. Byte or display is the same as there are
+ no multibyte characters earlier on the line. */
+ const int tab_col = 103;
+
+ /* Effective extra size of the tab beyond what a single space would have taken
+ up, indexed by tabstop. */
+ static const int num_tabstops = 11;
+ int extra_width[num_tabstops];
+ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
+ {
+ const int this_tab_size = tabstop - (tab_col - 1) % tabstop;
+ extra_width[tabstop] = this_tab_size - 1;
+ }
+ /* Example of this calculation: if tabstop is 10, the tab starting at column
+ #103 has to expand into 8 spaces, covering columns 103-110, so that the
+ next character is at column #111. So it takes up 7 more columns than
+ a space would have taken up. */
+ ASSERT_EQ (7, extra_width[10]);
+
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ line_table_test ltt (case_);
+
+ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1);
+
+ location_t line_end = linemap_position_for_column (line_table, line_bytes);
+
+ /* Don't attempt to run the tests if column data might be unavailable. */
+ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS)
+ return;
+
+ /* Check that cpp_display_width handles the tabs as expected. */
+ char_span lspan = location_get_source_line (tmp.get_filename (), 1);
+ ASSERT_EQ ('\t', *(lspan.get_buffer () + (tab_col - 1)));
+ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
+ {
+ ASSERT_EQ (line_bytes + extra_width[tabstop],
+ cpp_display_width (lspan.get_buffer (), lspan.length (),
+ tabstop));
+ ASSERT_EQ (line_bytes + extra_width[tabstop],
+ location_compute_display_column (expand_location (line_end),
+ tabstop));
+ }
+
+ /* Check that the tab is expanded to the expected number of spaces. */
+ rich_location richloc (line_table,
+ linemap_position_for_column (line_table,
+ tab_col + 1));
+ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
+ {
+ test_diagnostic_context dc;
+ dc.tabstop = tabstop;
+ layout test_layout (&dc, &richloc, DK_ERROR);
+ test_layout.print_line (1);
+ const char *out = pp_formatted_text (dc.printer);
+ ASSERT_EQ (NULL, strchr (out, '\t'));
+ const char *left_quote = strchr (out, '`');
+ const char *right_quote = strchr (out, '\'');
+ ASSERT_NE (NULL, left_quote);
+ ASSERT_NE (NULL, right_quote);
+ ASSERT_EQ (right_quote - left_quote, extra_width[tabstop] + 2);
+ }
+
+ /* Check that the line is offset properly and that the tab is broken up
+ into the expected number of spaces when it is the last character skipped
+ over. */
+ for (int tabstop = 1; tabstop != num_tabstops; ++tabstop)
+ {
+ test_diagnostic_context dc;
+ dc.tabstop = tabstop;
+ static const int small_width = 24;
+ dc.caret_max_width = small_width - 4;
+ dc.min_margin_width = test_left_margin - test_linenum_sep + 1;
+ dc.show_line_numbers_p = true;
+ layout test_layout (&dc, &richloc, DK_ERROR);
+ test_layout.print_line (1);
+
+ /* We have arranged things so that two columns will be printed before
+ the caret. If the tab results in more than one space, this should
+ produce two spaces in the output; otherwise, it will be a single space
+ preceded by the opening quote before the tab character. */
+ const char *output1
+ = " 1 | ' is a tab that occupies 1 byte and a variable number of "
+ "display columns, starting at column #103.\n"
+ " | ^\n\n";
+ const char *output2
+ = " 1 | ` ' is a tab that occupies 1 byte and a variable number of "
+ "display columns, starting at column #103.\n"
+ " | ^\n\n";
+ const char *expected_output = (extra_width[tabstop] ? output1 : output2);
+ ASSERT_STREQ (expected_output, pp_formatted_text (dc.printer));
+ }
+}
+
+
/* Verify that diagnostic_show_locus works sanely on UNKNOWN_LOCATION. */
static void
}
}
+/* Make sure that colorization codes don't interrupt a multibyte
+ sequence, which would corrupt it. */
+static void
+test_one_liner_colorized_utf8 ()
+{
+ test_diagnostic_context dc;
+ dc.colorize_source_p = true;
+ diagnostic_color_init (&dc, DIAGNOSTICS_COLOR_YES);
+ const location_t pi = linemap_position_for_column (line_table, 12);
+ rich_location richloc (line_table, pi);
+ diagnostic_show_locus (&dc, &richloc, DK_ERROR);
+
+ /* In order to avoid having the test depend on exactly how the colorization
+ was effected, just confirm there are two pi characters in the output. */
+ const char *result = pp_formatted_text (dc.printer);
+ const char *null_term = result + strlen (result);
+ const char *first_pi = strstr (result, "\xcf\x80");
+ ASSERT_TRUE (first_pi && first_pi <= null_term - 2);
+ ASSERT_STR_CONTAINS (first_pi + 2, "\xcf\x80");
+}
+
/* Run the various one-liner tests. */
static void
ASSERT_EQ (31, LOCATION_COLUMN (line_end));
char_span lspan = location_get_source_line (tmp.get_filename (), 1);
- ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length ()));
- ASSERT_EQ (25, location_compute_display_column (expand_location (line_end)));
+ ASSERT_EQ (25, cpp_display_width (lspan.get_buffer (), lspan.length (),
+ def_tabstop));
+ ASSERT_EQ (25, location_compute_display_column (expand_location (line_end),
+ def_tabstop));
test_one_liner_simple_caret_utf8 ();
test_one_liner_caret_and_range_utf8 ();
test_one_liner_many_fixits_1_utf8 ();
test_one_liner_many_fixits_2_utf8 ();
test_one_liner_labels_utf8 ();
+ test_one_liner_colorized_utf8 ();
}
/* Verify that gcc_rich_location::add_location_if_nearby works. */
/* Unit-test the line_corrections machinery. */
ASSERT_EQ (3, richloc.get_num_fixit_hints ());
const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
- ASSERT_EQ (column_range (12, 12), get_affected_range (hint_0, CU_BYTES));
ASSERT_EQ (column_range (12, 12),
- get_affected_range (hint_0, CU_DISPLAY_COLS));
- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0));
+ get_affected_range (&dc, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (12, 12),
+ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
+ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
- ASSERT_EQ (column_range (18, 18), get_affected_range (hint_1, CU_BYTES));
ASSERT_EQ (column_range (18, 18),
- get_affected_range (hint_1, CU_DISPLAY_COLS));
- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1));
+ get_affected_range (&dc, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (18, 18),
+ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
+ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
- ASSERT_EQ (column_range (29, 28), get_affected_range (hint_2, CU_BYTES));
ASSERT_EQ (column_range (29, 28),
- get_affected_range (hint_2, CU_DISPLAY_COLS));
- ASSERT_EQ (column_range (29, 29), get_printed_columns (hint_2));
+ get_affected_range (&dc, hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (29, 28),
+ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
+ ASSERT_EQ (column_range (29, 29), get_printed_columns (&dc, hint_2));
/* Add each hint in turn to a line_corrections instance,
and verify that they are consolidated into one correction instance
as expected. */
- line_corrections lc (tmp.get_filename (), 1);
+ line_corrections lc (&dc, tmp.get_filename (), 1);
/* The first replace hint by itself. */
lc.add_hint (hint_0);
/* Unit-test the line_corrections machinery. */
ASSERT_EQ (3, richloc.get_num_fixit_hints ());
const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
- ASSERT_EQ (column_range (14, 14), get_affected_range (hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (14, 14),
+ get_affected_range (&dc, hint_0, CU_BYTES));
ASSERT_EQ (column_range (12, 12),
- get_affected_range (hint_0, CU_DISPLAY_COLS));
- ASSERT_EQ (column_range (12, 22), get_printed_columns (hint_0));
+ get_affected_range (&dc, hint_0, CU_DISPLAY_COLS));
+ ASSERT_EQ (column_range (12, 22), get_printed_columns (&dc, hint_0));
const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
- ASSERT_EQ (column_range (22, 22), get_affected_range (hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (22, 22),
+ get_affected_range (&dc, hint_1, CU_BYTES));
ASSERT_EQ (column_range (18, 18),
- get_affected_range (hint_1, CU_DISPLAY_COLS));
- ASSERT_EQ (column_range (18, 20), get_printed_columns (hint_1));
+ get_affected_range (&dc, hint_1, CU_DISPLAY_COLS));
+ ASSERT_EQ (column_range (18, 20), get_printed_columns (&dc, hint_1));
const fixit_hint *hint_2 = richloc.get_fixit_hint (2);
- ASSERT_EQ (column_range (35, 34), get_affected_range (hint_2, CU_BYTES));
+ ASSERT_EQ (column_range (35, 34),
+ get_affected_range (&dc, hint_2, CU_BYTES));
ASSERT_EQ (column_range (30, 29),
- get_affected_range (hint_2, CU_DISPLAY_COLS));
- ASSERT_EQ (column_range (30, 30), get_printed_columns (hint_2));
+ get_affected_range (&dc, hint_2, CU_DISPLAY_COLS));
+ ASSERT_EQ (column_range (30, 30), get_printed_columns (&dc, hint_2));
/* Add each hint in turn to a line_corrections instance,
and verify that they are consolidated into one correction instance
as expected. */
- line_corrections lc (tmp.get_filename (), 1);
+ line_corrections lc (&dc, tmp.get_filename (), 1);
/* The first replace hint by itself. */
lc.add_hint (hint_0);
/* Two insertions, in the wrong order. */
{
+ test_diagnostic_context dc;
+
rich_location richloc (line_table, col_20);
richloc.add_fixit_insert_before (col_23, "{");
richloc.add_fixit_insert_before (col_21, "}");
/* These fixits should be accepted; they can't be consolidated. */
ASSERT_EQ (2, richloc.get_num_fixit_hints ());
const fixit_hint *hint_0 = richloc.get_fixit_hint (0);
- ASSERT_EQ (column_range (23, 22), get_affected_range (hint_0, CU_BYTES));
- ASSERT_EQ (column_range (23, 23), get_printed_columns (hint_0));
+ ASSERT_EQ (column_range (23, 22),
+ get_affected_range (&dc, hint_0, CU_BYTES));
+ ASSERT_EQ (column_range (23, 23), get_printed_columns (&dc, hint_0));
const fixit_hint *hint_1 = richloc.get_fixit_hint (1);
- ASSERT_EQ (column_range (21, 20), get_affected_range (hint_1, CU_BYTES));
- ASSERT_EQ (column_range (21, 21), get_printed_columns (hint_1));
+ ASSERT_EQ (column_range (21, 20),
+ get_affected_range (&dc, hint_1, CU_BYTES));
+ ASSERT_EQ (column_range (21, 21), get_printed_columns (&dc, hint_1));
/* Verify that they're printed correctly. */
- test_diagnostic_context dc;
diagnostic_show_locus (&dc, &richloc, DK_ERROR);
ASSERT_STREQ (" int a5[][0][0] = { 1, 2 };\n"
" ^\n"
pp_formatted_text (dc.printer));
}
+static void
+test_tab_expansion (const line_table_case &case_)
+{
+ /* Create a tempfile and write some text to it. This example uses a tabstop
+ of 8, as the column numbers attempt to indicate:
+
+ .....................000.01111111111.22222333333 display
+ .....................123.90123456789.56789012345 columns */
+ const char *content = " \t This: `\t' is a tab.\n";
+ /* ....................000 00000011111 11111222222 byte
+ ....................123 45678901234 56789012345 columns */
+
+ const int tabstop = 8;
+ const int first_non_ws_byte_col = 7;
+ const int right_quote_byte_col = 15;
+ const int last_byte_col = 25;
+ ASSERT_EQ (35, cpp_display_width (content, last_byte_col, tabstop));
+
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ line_table_test ltt (case_);
+ linemap_add (line_table, LC_ENTER, false, tmp.get_filename (), 1);
+
+ /* Don't attempt to run the tests if column data might be unavailable. */
+ location_t line_end = linemap_position_for_column (line_table, last_byte_col);
+ if (line_end > LINE_MAP_MAX_LOCATION_WITH_COLS)
+ return;
+
+ /* Check that the leading whitespace with mixed tabs and spaces is expanded
+ into 11 spaces. Recall that print_line() also puts one space before
+ everything too. */
+ {
+ test_diagnostic_context dc;
+ dc.tabstop = tabstop;
+ rich_location richloc (line_table,
+ linemap_position_for_column (line_table,
+ first_non_ws_byte_col));
+ layout test_layout (&dc, &richloc, DK_ERROR);
+ test_layout.print_line (1);
+ ASSERT_STREQ (" This: ` ' is a tab.\n"
+ " ^\n",
+ pp_formatted_text (dc.printer));
+ }
+
+ /* Confirm the display width was tracked correctly across the internal tab
+ as well. */
+ {
+ test_diagnostic_context dc;
+ dc.tabstop = tabstop;
+ rich_location richloc (line_table,
+ linemap_position_for_column (line_table,
+ right_quote_byte_col));
+ layout test_layout (&dc, &richloc, DK_ERROR);
+ test_layout.print_line (1);
+ ASSERT_STREQ (" This: ` ' is a tab.\n"
+ " ^\n",
+ pp_formatted_text (dc.printer));
+ }
+}
+
/* Verify that line numbers are correctly printed for the case of
a multiline range in which the width of the line numbers changes
(e.g. from "9" to "10"). */
test_layout_range_for_multiple_lines ();
for_each_line_table_case (test_layout_x_offset_display_utf8);
+ for_each_line_table_case (test_layout_x_offset_display_tab);
test_get_line_bytes_without_trailing_whitespace ();
for_each_line_table_case (test_fixit_insert_containing_newline_2);
for_each_line_table_case (test_fixit_replace_containing_newline);
for_each_line_table_case (test_fixit_deletion_affecting_newline);
+ for_each_line_table_case (test_tab_expansion);
test_line_numbers_multiline_range ();
}
#include "selftest.h"
#include "selftest-diagnostic.h"
#include "opts.h"
+#include "cpplib.h"
#ifdef HAVE_TERMIOS_H
# include <termios.h>
context->min_margin_width = 0;
context->show_ruler_p = false;
context->parseable_fixits_p = false;
+ context->column_unit = DIAGNOSTICS_COLUMN_UNIT_DISPLAY;
+ context->column_origin = 1;
+ context->tabstop = 8;
context->edit_context_ptr = NULL;
context->diagnostic_group_nesting_depth = 0;
context->diagnostic_group_emission_count = 0;
return diagnostic_kind_color[kind];
}
+/* Given an expanded_location, convert the column (which is in 1-based bytes)
+ to the requested units and origin. Return -1 if the column is
+ invalid (<= 0). */
+int
+diagnostic_converted_column (diagnostic_context *context, expanded_location s)
+{
+ if (s.column <= 0)
+ return -1;
+
+ int one_based_col;
+ switch (context->column_unit)
+ {
+ case DIAGNOSTICS_COLUMN_UNIT_DISPLAY:
+ one_based_col = location_compute_display_column (s, context->tabstop);
+ break;
+
+ case DIAGNOSTICS_COLUMN_UNIT_BYTE:
+ one_based_col = s.column;
+ break;
+
+ default:
+ gcc_unreachable ();
+ }
+
+ return one_based_col + (context->column_origin - 1);
+}
+
/* Return a formatted line and column ':%line:%column'. Elided if
- zero. The result is a statically allocated buffer. */
+ line == 0 or col < 0. (A column of 0 may be valid due to the
+ -fdiagnostics-column-origin option.)
+ The result is a statically allocated buffer. */
static const char *
maybe_line_and_column (int line, int col)
if (line)
{
- size_t l = snprintf (result, sizeof (result),
- col ? ":%d:%d" : ":%d", line, col);
+ size_t l
+ = snprintf (result, sizeof (result),
+ col >= 0 ? ":%d:%d" : ":%d", line, col);
gcc_checking_assert (l < sizeof (result));
}
else
const char *locus_cs = colorize_start (pp_show_color (pp), "locus");
const char *locus_ce = colorize_stop (pp_show_color (pp));
const char *file = s.file ? s.file : progname;
- int line = strcmp (file, N_("<built-in>")) ? s.line : 0;
- int col = context->show_column ? s.column : 0;
+ int line = 0;
+ int col = -1;
+ if (strcmp (file, N_("<built-in>")))
+ {
+ line = s.line;
+ if (context->show_column)
+ col = diagnostic_converted_column (context, s);
+ }
const char *line_col = maybe_line_and_column (line, col);
return build_message_string ("%s%s%s:%s", locus_cs, file,
if (! MAIN_FILE_P (map))
{
bool first = true;
+ expanded_location s = {};
do
{
where = linemap_included_from (map);
map = linemap_included_from_linemap (line_table, map);
- const char *line_col
- = maybe_line_and_column (SOURCE_LINE (map, where),
- first && context->show_column
- ? SOURCE_COLUMN (map, where) : 0);
+ s.file = LINEMAP_FILE (map);
+ s.line = SOURCE_LINE (map, where);
+ int col = -1;
+ if (first && context->show_column)
+ {
+ s.column = SOURCE_COLUMN (map, where);
+ col = diagnostic_converted_column (context, s);
+ }
+ const char *line_col = maybe_line_and_column (s.line, col);
static const char *const msgs[] =
{
N_("In file included from"),
unsigned index = !first;
pp_verbatim (context->printer, "%s%s %r%s%s%R",
first ? "" : ",\n", _(msgs[index]),
- "locus", LINEMAP_FILE (map), line_col);
+ "locus", s.file, line_col);
first = false;
}
while (! MAIN_FILE_P (map));
static void
assert_location_text (const char *expected_loc_text,
const char *filename, int line, int column,
- bool show_column)
+ bool show_column,
+ int origin = 1,
+ enum diagnostics_column_unit column_unit
+ = DIAGNOSTICS_COLUMN_UNIT_BYTE)
{
test_diagnostic_context dc;
dc.show_column = show_column;
+ dc.column_unit = column_unit;
+ dc.column_origin = origin;
expanded_location xloc;
xloc.file = filename;
assert_location_text ("PROGNAME:", NULL, 0, 0, true);
assert_location_text ("<built-in>:", "<built-in>", 42, 10, true);
assert_location_text ("foo.c:42:10:", "foo.c", 42, 10, true);
- assert_location_text ("foo.c:42:", "foo.c", 42, 0, true);
+ assert_location_text ("foo.c:42:9:", "foo.c", 42, 10, true, 0);
+ assert_location_text ("foo.c:42:1010:", "foo.c", 42, 10, true, 1001);
+ for (int origin = 0; origin != 2; ++origin)
+ assert_location_text ("foo.c:42:", "foo.c", 42, 0, true, origin);
assert_location_text ("foo.c:", "foo.c", 0, 10, true);
assert_location_text ("foo.c:42:", "foo.c", 42, 10, false);
assert_location_text ("foo.c:", "foo.c", 0, 10, false);
maybe_line_and_column (INT_MAX, INT_MAX);
maybe_line_and_column (INT_MIN, INT_MIN);
+ {
+ /* In order to test display columns vs byte columns, we need to create a
+ file for location_get_source_line() to read. */
+
+ const char *const content = "smile \xf0\x9f\x98\x82\n";
+ const int line_bytes = strlen (content) - 1;
+ const int def_tabstop = 8;
+ const int display_width = cpp_display_width (content, line_bytes,
+ def_tabstop);
+ ASSERT_EQ (line_bytes - 2, display_width);
+ temp_source_file tmp (SELFTEST_LOCATION, ".c", content);
+ const char *const fname = tmp.get_filename ();
+ const int buf_len = strlen (fname) + 16;
+ char *const expected = XNEWVEC (char, buf_len);
+
+ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes);
+ assert_location_text (expected, fname, 1, line_bytes, true,
+ 1, DIAGNOSTICS_COLUMN_UNIT_BYTE);
+
+ snprintf (expected, buf_len, "%s:1:%d:", fname, line_bytes - 1);
+ assert_location_text (expected, fname, 1, line_bytes, true,
+ 0, DIAGNOSTICS_COLUMN_UNIT_BYTE);
+
+ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width);
+ assert_location_text (expected, fname, 1, line_bytes, true,
+ 1, DIAGNOSTICS_COLUMN_UNIT_DISPLAY);
+
+ snprintf (expected, buf_len, "%s:1:%d:", fname, display_width - 1);
+ assert_location_text (expected, fname, 1, line_bytes, true,
+ 0, DIAGNOSTICS_COLUMN_UNIT_DISPLAY);
+
+ XDELETEVEC (expected);
+ }
+
+
progname = old_progname;
}
#include "pretty-print.h"
#include "diagnostic-core.h"
+/* An enum for controlling what units to use for the column number
+ when diagnostics are output, used by the -fdiagnostics-column-unit option.
+ Tabs will be expanded or not according to the value of -ftabstop. The origin
+ (default 1) is controlled by -fdiagnostics-column-origin. */
+
+enum diagnostics_column_unit
+{
+ /* The default from GCC 11 onwards: display columns. */
+ DIAGNOSTICS_COLUMN_UNIT_DISPLAY,
+
+ /* The behavior in GCC 10 and earlier: simple bytes. */
+ DIAGNOSTICS_COLUMN_UNIT_BYTE
+};
+
/* Enum for overriding the standard output format. */
enum diagnostics_output_format
rest of the diagnostic. */
bool parseable_fixits_p;
+ /* What units to use when outputting the column number. */
+ enum diagnostics_column_unit column_unit;
+
+ /* The origin for the column number (1-based or 0-based typically). */
+ int column_origin;
+
+ /* The size of the tabstop for tab expansion. */
+ int tabstop;
+
/* If non-NULL, an edit_context to which fix-it hints should be
applied, for generating patches. */
edit_context *edit_context_ptr;
}
extern const char *diagnostic_get_color_for_kind (diagnostic_t kind);
+extern int diagnostic_converted_column (diagnostic_context *context,
+ expanded_location s);
/* Pure text formatting support functions. */
extern char *file_name_as_prefix (diagnostic_context *, const char *);
/* Compute the number of digits in the decimal representation of an integer. */
extern int num_digits (int);
-extern json::value *json_from_expanded_location (location_t loc);
+extern json::value *json_from_expanded_location (diagnostic_context *context,
+ location_t loc);
#endif /* ! GCC_DIAGNOSTIC_H */
-fdiagnostics-show-template-tree -fno-elide-type @gol
-fdiagnostics-path-format=@r{[}none@r{|}separate-events@r{|}inline-events@r{]} @gol
-fdiagnostics-show-path-depths @gol
--fno-show-column}
+-fno-show-column @gol
+-fdiagnostics-column-unit=@r{[}display@r{|}byte@r{]} @gol
+-fdiagnostics-column-origin=@var{origin}}
@item Warning Options
@xref{Warning Options,,Options to Request or Suppress Warnings}.
diagnostics are being scanned by a program that does not understand the
column numbers, such as @command{dejagnu}.
+@item -fdiagnostics-column-unit=@var{UNIT}
+@opindex fdiagnostics-column-unit
+Select the units for the column number. This affects traditional diagnostics
+(in the absence of @option{-fno-show-column}), as well as JSON format
+diagnostics if requested.
+
+The default @var{UNIT}, @samp{display}, considers the number of display
+columns occupied by each character. This may be larger than the number
+of bytes required to encode the character, in the case of tab
+characters, or it may be smaller, in the case of multibyte characters.
+For example, the character ``GREEK SMALL LETTER PI (U+03C0)'' occupies one
+display column, and its UTF-8 encoding requires two bytes; the character
+``SLIGHTLY SMILING FACE (U+1F642)'' occupies two display columns, and
+its UTF-8 encoding requires four bytes.
+
+Setting @var{UNIT} to @samp{byte} changes the column number to the raw byte
+count in all cases, as was traditionally output by GCC prior to version 11.1.0.
+
+@item -fdiagnostics-column-origin=@var{ORIGIN}
+@opindex fdiagnostics-column-origin
+Select the origin for column numbers, i.e. the column number assigned to the
+first column. The default value of 1 corresponds to traditional GCC
+behavior and to the GNU style guide. Some utilities may perform better with an
+origin of 0; any non-negative value may be specified.
+
@item -fdiagnostics-format=@var{FORMAT}
@opindex fdiagnostics-format
Select a different format for printing diagnostics.
"locations": [
@{
"caret": @{
+ "display-column": 3,
+ "byte-column": 3,
"column": 3,
"file": "misleading-indentation.c",
"line": 15
@},
"finish": @{
+ "display-column": 4,
+ "byte-column": 4,
"column": 4,
"file": "misleading-indentation.c",
"line": 15
"locations": [
@{
"caret": @{
+ "display-column": 5,
+ "byte-column": 5,
"column": 5,
"file": "misleading-indentation.c",
"line": 17
"message": "...this statement, but the latter is @dots{}"
@}
]
+ "column-origin": 1,
@},
@dots{}
]
an @code{option} key describing the command-line option controlling the
warning.
-A diagnostic can contain zero or more locations. Each location has up
-to three positions within it: a @code{caret} position and optional
-@code{start} and @code{finish} positions. A location can also have
-an optional @code{label} string. For example, this error:
+A diagnostic can contain zero or more locations. Each location has an
+optional @code{label} string and up to three positions within it: a
+@code{caret} position and optional @code{start} and @code{finish} positions.
+A position is described by a @code{file} name, a @code{line} number, and
+three numbers indicating a column position:
+@itemize @bullet
+
+@item
+@code{display-column} counts display columns, accounting for tabs and
+multibyte characters.
+
+@item
+@code{byte-column} counts raw bytes.
+
+@item
+@code{column} is equal to one of
+the previous two, as dictated by the @option{-fdiagnostics-column-unit}
+option.
+
+@end itemize
+All three columns are relative to the origin specified by
+@option{-fdiagnostics-column-origin}, which is typically equal to 1 but may
+be set, for instance, to 0 for compatibility with other utilities that
+number columns from 0. The column origin is recorded in the JSON output in
+the @code{column-origin} tag. In the remaining examples below, the extra
+column number outputs have been omitted for brevity.
+
+For example, this error:
@smallexample
bad-binary-ops.c:64:23: error: invalid operands to binary + (have 'S' @{aka
source line in order to calculate the display width. If that cannot be done
for any reason, then returns the byte column as a fallback. */
int
-location_compute_display_column (expanded_location exploc)
+location_compute_display_column (expanded_location exploc, int tabstop)
{
if (!(exploc.file && *exploc.file && exploc.line && exploc.column))
return exploc.column;
/* If line is NULL, this function returns exploc.column which is the
desired fallback. */
return cpp_byte_column_to_display_column (line.get_buffer (), line.length (),
- exploc.column);
+ exploc.column, tabstop);
}
/* Dump statistics to stderr about the memory usage of the line_table
void test_cpp_utf8 ()
{
+ const int def_tabstop = 8;
/* Verify that wcwidth of invalid UTF-8 or control bytes is 1. */
{
- int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8);
+ int w_bad = cpp_display_width ("\xf0!\x9f!\x98!\x82!", 8, def_tabstop);
ASSERT_EQ (8, w_bad);
- int w_ctrl = cpp_display_width ("\r\t\n\v\0\1", 6);
- ASSERT_EQ (6, w_ctrl);
+ int w_ctrl = cpp_display_width ("\r\n\v\0\1", 5, def_tabstop);
+ ASSERT_EQ (5, w_ctrl);
}
/* Verify that wcwidth of valid UTF-8 is as expected. */
{
- const int w_pi = cpp_display_width ("\xcf\x80", 2);
+ const int w_pi = cpp_display_width ("\xcf\x80", 2, def_tabstop);
ASSERT_EQ (1, w_pi);
- const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4);
+ const int w_emoji = cpp_display_width ("\xf0\x9f\x98\x82", 4, def_tabstop);
ASSERT_EQ (2, w_emoji);
- const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2);
+ const int w_umlaut_precomposed = cpp_display_width ("\xc3\xbf", 2,
+ def_tabstop);
ASSERT_EQ (1, w_umlaut_precomposed);
- const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3);
+ const int w_umlaut_combining = cpp_display_width ("y\xcc\x88", 3,
+ def_tabstop);
ASSERT_EQ (1, w_umlaut_combining);
- const int w_han = cpp_display_width ("\xe4\xb8\xba", 3);
+ const int w_han = cpp_display_width ("\xe4\xb8\xba", 3, def_tabstop);
ASSERT_EQ (2, w_han);
- const int w_ascii = cpp_display_width ("GCC", 3);
+ const int w_ascii = cpp_display_width ("GCC", 3, def_tabstop);
ASSERT_EQ (3, w_ascii);
const int w_mixed = cpp_display_width ("\xcf\x80 = 3.14 \xf0\x9f\x98\x82"
- "\x9f! \xe4\xb8\xba y\xcc\x88", 24);
+ "\x9f! \xe4\xb8\xba y\xcc\x88",
+ 24, def_tabstop);
ASSERT_EQ (18, w_mixed);
}
+ /* Verify that display width properly expands tabs. */
+ {
+ const char *tstr = "\tabc\td";
+ ASSERT_EQ (6, cpp_display_width (tstr, 6, 1));
+ ASSERT_EQ (10, cpp_display_width (tstr, 6, 3));
+ ASSERT_EQ (17, cpp_display_width (tstr, 6, 8));
+ ASSERT_EQ (1, cpp_display_column_to_byte_column (tstr, 6, 7, 8));
+ }
+
/* Verify that cpp_byte_column_to_display_column can go past the end,
and similar edge cases. */
{
/* 111122223456
Byte columns. */
- ASSERT_EQ (5, cpp_display_width (str, 6));
- ASSERT_EQ (105, cpp_byte_column_to_display_column (str, 6, 106));
- ASSERT_EQ (10000, cpp_byte_column_to_display_column (NULL, 0, 10000));
- ASSERT_EQ (0, cpp_byte_column_to_display_column (NULL, 10000, 0));
+ ASSERT_EQ (5, cpp_display_width (str, 6, def_tabstop));
+ ASSERT_EQ (105,
+ cpp_byte_column_to_display_column (str, 6, 106, def_tabstop));
+ ASSERT_EQ (10000,
+ cpp_byte_column_to_display_column (NULL, 0, 10000, def_tabstop));
+ ASSERT_EQ (0,
+ cpp_byte_column_to_display_column (NULL, 10000, 0, def_tabstop));
}
/* Verify that cpp_display_column_to_byte_column can go past the end,
/* 000000000000000000000000000000000111111
111122223333444456666777788889999012345
Byte columns. */
- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2));
- ASSERT_EQ (15, cpp_display_column_to_byte_column (str, 15, 11));
- ASSERT_EQ (115, cpp_display_column_to_byte_column (str, 15, 111));
- ASSERT_EQ (10000, cpp_display_column_to_byte_column (NULL, 0, 10000));
- ASSERT_EQ (0, cpp_display_column_to_byte_column (NULL, 10000, 0));
+ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 2, def_tabstop));
+ ASSERT_EQ (15,
+ cpp_display_column_to_byte_column (str, 15, 11, def_tabstop));
+ ASSERT_EQ (115,
+ cpp_display_column_to_byte_column (str, 15, 111, def_tabstop));
+ ASSERT_EQ (10000,
+ cpp_display_column_to_byte_column (NULL, 0, 10000, def_tabstop));
+ ASSERT_EQ (0,
+ cpp_display_column_to_byte_column (NULL, 10000, 0, def_tabstop));
/* Verify that we do not interrupt a UTF-8 sequence. */
- ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1));
+ ASSERT_EQ (4, cpp_display_column_to_byte_column (str, 15, 1, def_tabstop));
for (int byte_col = 1; byte_col <= 15; ++byte_col)
{
- const int disp_col = cpp_byte_column_to_display_column (str, 15,
- byte_col);
- const int byte_col2 = cpp_display_column_to_byte_column (str, 15,
- disp_col);
+ const int disp_col
+ = cpp_byte_column_to_display_column (str, 15, byte_col, def_tabstop);
+ const int byte_col2
+ = cpp_display_column_to_byte_column (str, 15, disp_col, def_tabstop);
/* If we ask for the display column in the middle of a UTF-8
sequence, it will return the length of the partial sequence,
extern bool is_location_from_builtin_token (location_t);
extern expanded_location expand_location (location_t);
-extern int location_compute_display_column (expanded_location);
+
+extern int location_compute_display_column (expanded_location exploc,
+ int tabstop);
/* A class capturing the bounds of a buffer, to allow for run-time
bounds-checking in a checked build. */
dc->parseable_fixits_p = value;
break;
+ case OPT_fdiagnostics_column_unit_:
+ dc->column_unit = (enum diagnostics_column_unit)value;
+ break;
+
+ case OPT_fdiagnostics_column_origin_:
+ dc->column_origin = value;
+ break;
+
case OPT_fdiagnostics_show_cwe:
dc->show_cwe = value;
break;
check_alignment_argument (loc, arg, "functions");
break;
+ case OPT_ftabstop_:
+ /* It is documented that we silently ignore silly values. */
+ if (value >= 1 && value <= 100)
+ dc->tabstop = value;
+ break;
+
default:
/* If the flag was handled in a standard way, assume the lack of
processing here is intentional. */
/* ... */
if ((err = foo (a)) != 0)
goto fail;
- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */
+ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */
goto fail;
- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
+ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
if ((err = foo (c)) != 0)
goto fail;
/* ... */
/* { dg-begin-multiline-output "" }
- if ((err = foo (b)) != 0)
- ^~
+ if ((err = foo (b)) != 0)
+ ^~
{ dg-end-multiline-output "" } */
/* { dg-begin-multiline-output "" }
- goto fail;
- ^~~~
+ goto fail;
+ ^~~~
{ dg-end-multiline-output "" } */
fail:
/* ... */
if ((err = foo (a)) != 0)
goto fail;
- if ((err = foo (b)) != 0) /* { dg-message "2: this 'if' clause does not guard..." } */
+ if ((err = foo (b)) != 0) /* { dg-message "9: this 'if' clause does not guard..." } */
goto fail;
- goto fail; /* { dg-message "3: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
+ goto fail; /* { dg-message "17: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
if ((err = foo (c)) != 0)
goto fail;
/* ... */
while (flagA)
if (flagB) /* { dg-message "7: this 'if' clause does not guard..." } */
foo (0);
- foo (1);/* { dg-message "2: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
+ foo (1);/* { dg-message "9: ...this statement, but the latter is misleadingly indented as if it were guarded by the 'if'" } */
}
void fn_17_spaces (void)
We can't rely on any ordering of the keys. */
/* { dg-regexp "\"kind\": \"error\"" } */
+/* { dg-regexp "\"column-origin\": 1" } */
/* { dg-regexp "\"message\": \"#error message\"" } */
/* { dg-regexp "\"caret\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */
/* { dg-regexp "\"line\": 4" } */
/* { dg-regexp "\"column\": 2" } */
+/* { dg-regexp "\"display-column\": 2" } */
+/* { dg-regexp "\"byte-column\": 2" } */
/* { dg-regexp "\"finish\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.c\"" } */
/* { dg-regexp "\"line\": 4" } */
/* { dg-regexp "\"column\": 6" } */
+/* { dg-regexp "\"display-column\": 6" } */
+/* { dg-regexp "\"byte-column\": 6" } */
/* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
/* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
We can't rely on any ordering of the keys. */
/* { dg-regexp "\"kind\": \"warning\"" } */
+/* { dg-regexp "\"column-origin\": 1" } */
/* { dg-regexp "\"message\": \"#warning message\"" } */
/* { dg-regexp "\"option\": \"-Wcpp\"" } */
/* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */
/* { dg-regexp "\"line\": 4" } */
/* { dg-regexp "\"column\": 2" } */
+/* { dg-regexp "\"display-column\": 2" } */
+/* { dg-regexp "\"byte-column\": 2" } */
/* { dg-regexp "\"finish\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.c\"" } */
/* { dg-regexp "\"line\": 4" } */
/* { dg-regexp "\"column\": 8" } */
+/* { dg-regexp "\"display-column\": 8" } */
+/* { dg-regexp "\"byte-column\": 8" } */
/* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
/* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
We can't rely on any ordering of the keys. */
/* { dg-regexp "\"kind\": \"error\"" } */
+/* { dg-regexp "\"column-origin\": 1" } */
/* { dg-regexp "\"message\": \"#warning message\"" } */
/* { dg-regexp "\"option\": \"-Werror=cpp\"" } */
/* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wcpp\"" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */
/* { dg-regexp "\"line\": 4" } */
/* { dg-regexp "\"column\": 2" } */
+/* { dg-regexp "\"display-column\": 2" } */
+/* { dg-regexp "\"byte-column\": 2" } */
/* { dg-regexp "\"finish\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.c\"" } */
/* { dg-regexp "\"line\": 4" } */
/* { dg-regexp "\"column\": 8" } */
+/* { dg-regexp "\"display-column\": 8" } */
+/* { dg-regexp "\"byte-column\": 8" } */
/* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
/* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
/* { dg-regexp "\"line\": 8" } */
/* { dg-regexp "\"column\": 5" } */
+/* { dg-regexp "\"display-column\": 5" } */
+/* { dg-regexp "\"byte-column\": 5" } */
/* { dg-regexp "\"finish\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
/* { dg-regexp "\"line\": 8" } */
/* { dg-regexp "\"column\": 10" } */
+/* { dg-regexp "\"display-column\": 10" } */
+/* { dg-regexp "\"byte-column\": 10" } */
/* The outer diagnostic. */
/* { dg-regexp "\"kind\": \"warning\"" } */
+/* { dg-regexp "\"column-origin\": 1" } */
/* { dg-regexp "\"message\": \"this 'if' clause does not guard...\"" } */
/* { dg-regexp "\"option\": \"-Wmisleading-indentation\"" } */
/* { dg-regexp "\"option_url\": \"https:\[^\n\r\"\]*#index-Wmisleading-indentation\"" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
/* { dg-regexp "\"line\": 6" } */
/* { dg-regexp "\"column\": 3" } */
+/* { dg-regexp "\"display-column\": 3" } */
+/* { dg-regexp "\"byte-column\": 3" } */
/* { dg-regexp "\"finish\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-4.c\"" } */
/* { dg-regexp "\"line\": 6" } */
/* { dg-regexp "\"column\": 4" } */
+/* { dg-regexp "\"display-column\": 4" } */
+/* { dg-regexp "\"byte-column\": 4" } */
/* More from the nested diagnostic (we can't guarantee what order the
"file" keys are consumed). */
We can't rely on any ordering of the keys. */
/* { dg-regexp "\"kind\": \"error\"" } */
+/* { dg-regexp "\"column-origin\": 1" } */
/* { dg-regexp "\"message\": \".*\"" } */
/* Verify fix-it hints. */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
/* { dg-regexp "\"line\": 8" } */
/* { dg-regexp "\"column\": 15" } */
+/* { dg-regexp "\"display-column\": 15" } */
+/* { dg-regexp "\"byte-column\": 15" } */
/* { dg-regexp "\"next\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
/* { dg-regexp "\"line\": 8" } */
/* { dg-regexp "\"column\": 21" } */
+/* { dg-regexp "\"display-column\": 21" } */
+/* { dg-regexp "\"byte-column\": 21" } */
/* { dg-regexp "\"fixits\": \[\[\{\}, \]*\]" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
/* { dg-regexp "\"line\": 8" } */
/* { dg-regexp "\"column\": 15" } */
+/* { dg-regexp "\"display-column\": 15" } */
+/* { dg-regexp "\"byte-column\": 15" } */
/* { dg-regexp "\"finish\": \{" } */
/* { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-5.c\"" } */
/* { dg-regexp "\"line\": 8" } */
/* { dg-regexp "\"column\": 20" } */
+/* { dg-regexp "\"display-column\": 20" } */
+/* { dg-regexp "\"byte-column\": 20" } */
/* { dg-regexp "\"locations\": \[\[\{\}, \]*\]" } */
/* { dg-regexp "\"children\": \[\[\]\[\]\]" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -Wmultichar" } */
+
+/* column units: bytes (via arg)
+ column origin: 1 (via default)
+ tabstop: 8 (via default) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -Wmultichar" } */
+
+/* column units: display (via arg)
+ column origin: 1 (via default)
+ tabstop: 8 (via default) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "18: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "25: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=200 -Wmultichar" } */
+
+/* column units: bytes (via arg)
+ column origin: 1 (via fallback from overly large argument)
+ tabstop: 8 (via default) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "18: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "19: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */
+
+/* column units: bytes (via arg)
+ column origin: 0 (via arg)
+ tabstop: 8 (via default) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "10: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "18: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=display -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=0 -Wmultichar" } */
+
+/* column units: display (via arg)
+ column origin: 0 (via arg)
+ tabstop: 8 (via default) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "17: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "17: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "24: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -fdiagnostics-column-origin=100 -Wmultichar" } */
+
+/* column units: bytes (via arg)
+ column origin: 100 (via arg)
+ tabstop: 8 (via default) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "110: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "117: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "118: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fdiagnostics-column-unit=byte -fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */
+
+/* column units: bytes (via arg)
+ column origin: 1 (via default)
+ tabstop: 9 (via arg) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "11: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "20: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-fshow-column -fdiagnostics-show-caret -ftabstop=9 -Wmultichar" } */
+
+/* column units: display (via default)
+ column origin: 1 (via default)
+ tabstop: 9 (via arg) */
+
+/* This line starts with a tab. */
+ int c1 = 'c1'; /* { dg-warning "19: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c1 = 'c1';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces. */
+ int c2 = 'c2'; /* { dg-warning "19: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c2 = 'c2';
+ ^~~~
+ { dg-end-multiline-output "" } */
+
+/* This line starts with <tabstop> spaces and has an internal tab after
+ a space. */
+ int c3 = 'c3'; /* { dg-warning "28: multi-character character constant" } */
+/* { dg-begin-multiline-output "" }
+ int c3 = 'c3';
+ ^~~~
+ { dg-end-multiline-output "" } */
_Static_assert(sizeof(int) >= sizeof(char), /* { dg-message "to match this '\\('" } */
"msg"; /* { dg-error "expected '\\)' before ';' token" } */
/* { dg-begin-multiline-output "" }
- "msg";
- ^
- )
+ "msg";
+ ^
+ )
{ dg-end-multiline-output "" } */
/* { dg-begin-multiline-output "" }
_Static_assert(sizeof(int) >= sizeof(char),
~~~~~~~~~~~~~~~~
|
s
- + some_other_function ());
- ^ ~~~~~~~~~~~~~~~~~~~~~~
- |
- t
+ + some_other_function ());
+ ^ ~~~~~~~~~~~~~~~~~~~~~~
+ |
+ t
{ dg-end-multiline-output "" } */
}
int);
};
-// { dg-error "4:'itn' has not been declared" "" { target *-*-* } 6 }
+// { dg-error "18:'itn' has not been declared" "" { target *-*-* } 6 }
int h;
A() { i=10; j=20; }
virtual void f1() { printf("i=%d j=%d\n",i,j); }
- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" }
+ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" }
};
class B : public A {
public:
virtual void f1() { printf("i=%d j=%d\n",i,j); }// { dg-error "" } member.*// ERROR - member.*
- friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "9:virtual functions cannot be friends" }
+ friend virtual void f2() { printf("i=%d j=%d\n",i,j); } // { dg-error "16:virtual functions cannot be friends" }
// { dg-error "private" "" { target *-*-* } .-1 }
};
main()
{
C<char*> c;
- char* p = Z(c.O); //{ dg-error "13:'Z' was not declared" } ambiguous c.O
+ char* p = Z(c.O); //{ dg-error "29:'Z' was not declared" } ambiguous c.O
}
// The compiler does not like this line!!!!!!
typename Graph<VertexType, EdgeType>::Successor::iterator
- startN = G[i].second.begin(), // { dg-error "14:no match" } no index operator
- endN = G[i].second.end(); // { dg-error "14:no match" } no index operator
+ startN = G[i].second.begin(), // { dg-error "21:no match" } no index operator
+ endN = G[i].second.end(); // { dg-error "21:no match" } no index operator
while(startN != endN)
{
| | ~~~~~~~~~~
| | |
| | (4) ...to here
- | NN | to dereference it above
+ | NN | to dereference it above
| NN | return *ptr;
| | ~~~~
| | |
~~~~~~~~~~~~~~~~
|
struct s
- + some_other_function ());
- ^ ~~~~~~~~~~~~~~~~~~~~~~
- |
- struct t
+ + some_other_function ());
+ ^ ~~~~~~~~~~~~~~~~~~~~~~
+ |
+ struct t
{ dg-end-multiline-output "" } */
}
{
printf ((nfoo > 1) ? "%d foos" : "%d foo", nfoo);
printf ((l > 1) ? "%d foos" /* { dg-warning "23:int" "wrong type in conditional expr" } */
- : "%d foo", l); /* { dg-warning "16:int" "wrong type in conditional expr" } */
+ : "%d foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */
printf ((l > 1) ? "%ld foos" : "%d foo", l); /* { dg-warning "36:int" "wrong type in conditional expr" } */
printf ((l > 1) ? "%d foos" : "%ld foo", l); /* { dg-warning "23:int" "wrong type in conditional expr" } */
/* Should allow one case to have extra arguments. */
"Allow peer ports on the same physical port to login to each "
"other.");
-/* { dg-warning "6: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */
+/* { dg-warning "20: format .%d. expects argument of type .int., but argument 4 has type .unsigned int. " "" { target *-*-* } .-12 } */
__emit_expression_range (0,
f (i) + __builtin_types_compatible_p (long, int)); /* { dg-warning "range" } */
/* { dg-begin-multiline-output "" }
- f (i) + __builtin_types_compatible_p (long, int));
- ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ f (i) + __builtin_types_compatible_p (long, int));
+ ~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{ dg-end-multiline-output "" } */
__emit_expression_range (0,
__builtin_types_compatible_p (long, int) + f (i)); /* { dg-warning "range" } */
/* { dg-begin-multiline-output "" }
- __builtin_types_compatible_p (long, int) + f (i));
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
+ __builtin_types_compatible_p (long, int) + f (i));
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
{ dg-end-multiline-output "" } */
}
/* { dg-begin-multiline-output "" }
__emit_expression_range (0, foo (0,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789"));
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789"));
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
{ dg-end-multiline-output "" } */
/* Another expression that transitions between ordinary maps; this
/* { dg-begin-multiline-output "" }
__emit_expression_range (0, foo (0, "01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789",
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- 0));
- ~~
+ 0));
+ ~~
{ dg-end-multiline-output "" } */
}
/* { dg-error "unable to read substring location: unable to read source line" "" { target c } 329 } */
/* { dg-error "unable to read substring location: failed to get ordinary maps" "" { target c++ } 329 } */
/* { dg-begin-multiline-output "" }
- __emit_string_literal_range(__FILE__":%5d: " format, \
+ __emit_string_literal_range(__FILE__":%5d: " format, \
^~~~~~~~
{ dg-end-multiline-output "" { target c } } */
/* { dg-begin-multiline-output "" }
- __emit_string_literal_range(__FILE__":%5d: " format, \
+ __emit_string_literal_range(__FILE__":%5d: " format, \
^
{ dg-end-multiline-output "" { target c++ } } */
/* Should get format warnings even though the built-in declaration
isn't "visible". */
printf (
- "%s", 1); /* { dg-warning "8:format" } */
+ "%s", 1); /* { dg-warning "15:format" } */
/* The type of strcmp here should have no prototype. */
if (0)
strcmp (1);
! We can't rely on any ordering of the keys.
! { dg-regexp "\"kind\": \"error\"" }
+! { dg-regexp "\"column-origin\": 1" }
! { dg-regexp "\"message\": \"#error message\"" }
! { dg-regexp "\"caret\": \{" }
! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" }
! { dg-regexp "\"line\": 4" }
! { dg-regexp "\"column\": 2" }
+! { dg-regexp "\"display-column\": 2" }
+! { dg-regexp "\"byte-column\": 2" }
! { dg-regexp "\"finish\": \{" }
! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-1.F90\"" }
! { dg-regexp "\"line\": 4" }
! { dg-regexp "\"column\": 6" }
+! { dg-regexp "\"display-column\": 6" }
+! { dg-regexp "\"byte-column\": 6" }
! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" }
! { dg-regexp "\"children\": \[\[\]\[\]\]" }
! We can't rely on any ordering of the keys.
! { dg-regexp "\"kind\": \"warning\"" }
+! { dg-regexp "\"column-origin\": 1" }
! { dg-regexp "\"message\": \"#warning message\"" }
! { dg-regexp "\"option\": \"-Wcpp\"" }
! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" }
! { dg-regexp "\"line\": 4" }
! { dg-regexp "\"column\": 2" }
+! { dg-regexp "\"display-column\": 2" }
+! { dg-regexp "\"byte-column\": 2" }
! { dg-regexp "\"finish\": \{" }
! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-2.F90\"" }
! { dg-regexp "\"line\": 4" }
! { dg-regexp "\"column\": 8" }
+! { dg-regexp "\"display-column\": 8" }
+! { dg-regexp "\"byte-column\": 8" }
! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" }
! { dg-regexp "\"children\": \[\[\]\[\]\]" }
! We can't rely on any ordering of the keys.
! { dg-regexp "\"kind\": \"error\"" }
+! { dg-regexp "\"column-origin\": 1" }
! { dg-regexp "\"message\": \"#warning message\"" }
! { dg-regexp "\"option\": \"-Werror=cpp\"" }
! { dg-regexp "\"option_url\": \"\[^\n\r\"\]*#index-Wcpp\"" }
! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" }
! { dg-regexp "\"line\": 4" }
! { dg-regexp "\"column\": 2" }
+! { dg-regexp "\"display-column\": 2" }
+! { dg-regexp "\"byte-column\": 2" }
! { dg-regexp "\"finish\": \{" }
! { dg-regexp "\"file\": \"\[^\n\r\"\]*diagnostic-format-json-3.F90\"" }
! { dg-regexp "\"line\": 4" }
! { dg-regexp "\"column\": 8" }
+! { dg-regexp "\"display-column\": 8" }
+! { dg-regexp "\"byte-column\": 8" }
! { dg-regexp "\"locations\": \[\[\{\}, \]*\]" }
! { dg-regexp "\"children\": \[\[\]\[\]\]" }
// { dg-do compile }
// { dg-options "-fgo-debug-optimization" }
+// This comment is necessary to work around a dejagnu bug. Otherwise, the
+// column of the second error message would equal the row of the first one, and
+// since the errors are also identical, dejagnu is not able to distinguish them.
package p
doesn't have access to trees (for m_fndecl). */
json::value *
-default_tree_make_json_for_path (diagnostic_context *,
+default_tree_make_json_for_path (diagnostic_context *context,
const diagnostic_path *path)
{
json::array *path_array = new json::array ();
json::object *event_obj = new json::object ();
if (event.get_location ())
event_obj->set ("location",
- json_from_expanded_location (event.get_location ()));
+ json_from_expanded_location (context,
+ event.get_location ()));
label_text event_text (event.get_desc (false));
event_obj->set ("description", new json::string (event_text.m_buffer));
event_text.maybe_free ();
return result;
}
-/* Helper for cpp_byte_column_to_display_column and its inverse. Given a
- pointer to a UTF-8-encoded character, compute its display width. *INBUFP
- points on entry to the start of the UTF-8 encoding of the character, and
- is updated to point just after the last byte of the encoding. *INBYTESLEFTP
- contains on entry the remaining size of the buffer into which *INBUFP
- points, and this is also updated accordingly. If *INBUFP does not
+cpp_display_width_computation::
+cpp_display_width_computation (const char *data, int data_length, int tabstop) :
+ m_begin (data),
+ m_next (m_begin),
+ m_bytes_left (data_length),
+ m_tabstop (tabstop),
+ m_display_cols (0)
+{
+ gcc_assert (m_tabstop > 0);
+}
+
+
+/* The main implementation function for class cpp_display_width_computation.
+ m_next points on entry to the start of the UTF-8 encoding of the next
+ character, and is updated to point just after the last byte of the encoding.
+ m_bytes_left contains on entry the remaining size of the buffer into which
+ m_next points, and this is also updated accordingly. If m_next does not
point to a valid UTF-8-encoded sequence, then it will be treated as a single
- byte with display width 1. */
+ byte with display width 1. m_cur_display_col is the current display column,
+ relative to which tab stops should be expanded. Returns the display width of
+ the codepoint just processed. */
-static inline int
-compute_next_display_width (const uchar **inbufp, size_t *inbytesleftp)
+int
+cpp_display_width_computation::process_next_codepoint ()
{
cppchar_t c;
- if (one_utf8_to_cppchar (inbufp, inbytesleftp, &c) != 0)
+ int next_width;
+
+ if (*m_next == '\t')
+ {
+ ++m_next;
+ --m_bytes_left;
+ next_width = m_tabstop - (m_display_cols % m_tabstop);
+ }
+ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
+ != 0)
{
/* Input is not convertible to UTF-8. This could be fine, e.g. in a
string literal, so don't complain. Just treat it as if it has a width
of one. */
- ++*inbufp;
- --*inbytesleftp;
- return 1;
+ ++m_next;
+ --m_bytes_left;
+ next_width = 1;
+ }
+ else
+ {
+ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */
+ next_width = cpp_wcwidth (c);
}
- /* one_utf8_to_cppchar() has updated inbufp and inbytesleftp for us. */
- return cpp_wcwidth (c);
+ m_display_cols += next_width;
+ return next_width;
+}
+
+/* Utility to advance the byte stream by the minimum amount needed to consume
+ N display columns. Returns the number of display columns that were
+ actually skipped. This could be less than N, if there was not enough data,
+ or more than N, if the last character to be skipped had a sufficiently large
+ display width. */
+int
+cpp_display_width_computation::advance_display_cols (int n)
+{
+ const int start = m_display_cols;
+ const int target = start + n;
+ while (m_display_cols < target && !done ())
+ process_next_codepoint ();
+ return m_display_cols - start;
}
/* For the string of length DATA_LENGTH bytes that begins at DATA, compute
how many display columns are occupied by the first COLUMN bytes. COLUMN
may exceed DATA_LENGTH, in which case the phantom bytes at the end are
- treated as if they have display width 1. */
+ treated as if they have display width 1. Tabs are expanded to the next tab
+ stop, relative to the start of DATA. */
int
cpp_byte_column_to_display_column (const char *data, int data_length,
- int column)
+ int column, int tabstop)
{
- int display_col = 0;
- const uchar *udata = (const uchar *) data;
const int offset = MAX (0, column - data_length);
- size_t inbytesleft = column - offset;
- while (inbytesleft)
- display_col += compute_next_display_width (&udata, &inbytesleft);
- return display_col + offset;
+ cpp_display_width_computation dw (data, column - offset, tabstop);
+ while (!dw.done ())
+ dw.process_next_codepoint ();
+ return dw.display_cols_processed () + offset;
}
/* For the string of length DATA_LENGTH bytes that begins at DATA, compute
int
cpp_display_column_to_byte_column (const char *data, int data_length,
- int display_col)
+ int display_col, int tabstop)
{
- int column = 0;
- const uchar *udata = (const uchar *) data;
- size_t inbytesleft = data_length;
- while (column < display_col && inbytesleft)
- column += compute_next_display_width (&udata, &inbytesleft);
- return data_length - inbytesleft + MAX (0, display_col - column);
+ cpp_display_width_computation dw (data, data_length, tabstop);
+ const int avail_display = dw.advance_display_cols (display_col);
+ return dw.bytes_processed () + MAX (0, display_col - avail_display);
}
/* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc,
carries all the options visible to the command line. */
struct cpp_options
{
- /* Characters between tab stops. */
- unsigned int tabstop;
-
/* The language we're preprocessing. */
enum c_lang lang;
(const cpp_token *);
/* In charset.c */
+
+/* A class to manage the state while converting a UTF-8 sequence to cppchar_t
+ and computing the display width one character at a time. */
+class cpp_display_width_computation {
+ public:
+ cpp_display_width_computation (const char *data, int data_length,
+ int tabstop);
+ const char *next_byte () const { return m_next; }
+ int bytes_processed () const { return m_next - m_begin; }
+ int bytes_left () const { return m_bytes_left; }
+ bool done () const { return !bytes_left (); }
+ int display_cols_processed () const { return m_display_cols; }
+
+ int process_next_codepoint ();
+ int advance_display_cols (int n);
+
+ private:
+ const char *const m_begin;
+ const char *m_next;
+ size_t m_bytes_left;
+ const int m_tabstop;
+ int m_display_cols;
+};
+
+/* Convenience functions that are simple use cases for class
+ cpp_display_width_computation. Tab characters will be expanded to spaces
+ as determined by TABSTOP. */
int cpp_byte_column_to_display_column (const char *data, int data_length,
- int column);
-inline int cpp_display_width (const char *data, int data_length)
+ int column, int tabstop);
+inline int cpp_display_width (const char *data, int data_length,
+ int tabstop)
{
- return cpp_byte_column_to_display_column (data, data_length, data_length);
+ return cpp_byte_column_to_display_column (data, data_length, data_length,
+ tabstop);
}
int cpp_display_column_to_byte_column (const char *data, int data_length,
- int display_col);
+ int display_col, int tabstop);
int cpp_wcwidth (cppchar_t c);
#endif /* ! LIBCPP_CPPLIB_H */
CPP_OPTION (pfile, discard_comments) = 1;
CPP_OPTION (pfile, discard_comments_in_macro_exp) = 1;
CPP_OPTION (pfile, max_include_depth) = 200;
- CPP_OPTION (pfile, tabstop) = 8;
CPP_OPTION (pfile, operator_names) = 1;
CPP_OPTION (pfile, warn_trigraphs) = 2;
CPP_OPTION (pfile, warn_endif_labels) = 1;
projects / gcc.git / commitdiff