On Do, 19 Nov 2015, Bram Moolenaar wrote:
> Christian Brabandt wrote:
>
> > On Fr, 13 Nov 2015, Christian Brabandt wrote:
> > > On Di, 10 Nov 2015, [email protected] wrote:
> > > > Could we have a countword() function that would avoid such dirty tricks?
> > > I'll look into this.
> >
> > Attached is a patch.
>
> Thanks. I think the help should mention that it's the same info as g
> CTRL-G. And g CTRL-G should mention wordcount().
>
> Should not be too difficult to write a test.
Updated patch including tests attached.
Best,
Christian
--
Das Leben ist eine Tragödie für die, die fühlen, und eine Komödie für
die, die denken.
-- Jean de la Bruyère
--
--
You received this message from the "vim_dev" maillist.
Do not top-post! Type your reply below the text you are replying to.
For more information, visit http://www.vim.org/maillist.php
---
You received this message because you are subscribed to the Google Groups
"vim_dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
diff --git a/runtime/doc/editing.txt b/runtime/doc/editing.txt
--- a/runtime/doc/editing.txt
+++ b/runtime/doc/editing.txt
@@ -78,7 +78,8 @@ g CTRL-G Prints the current position of
than one position on the screen (<Tab> or special
character), both the "real" column and the screen
column are shown, separated with a dash.
- See also 'ruler' option. {not in Vi}
+ See also 'ruler' option and |wordcount()| function.
+ {not in Vi}
*v_g_CTRL-G*
{Visual}g CTRL-G Similar to "g CTRL-G", but Word, Character, Line, and
diff --git a/runtime/doc/eval.txt b/runtime/doc/eval.txt
--- a/runtime/doc/eval.txt
+++ b/runtime/doc/eval.txt
@@ -6686,6 +6686,28 @@ winwidth({nr}) *winwidth()*
: exe "normal 50\<C-W>|"
:endif
<
+wordcount() *wordcount()*
+ The result is a dictionary of byte/chars/word statistics for
+ the current buffer. This is the same info as provided by
+ |g_CTRL-G|
+ The return value includes:
+ chars Number of chars in the buffer
+ words Number of words in the buffer
+ bytes Number of bytes in the buffer
+ cursor_chars Number of chars before cursor position
+ (not in Visual mode)
+ cursor_bytes Number of bytes before cursor position
+ (not in Visual mode)
+ cursor_words Number of words before cursor position
+ (not in Visual mode)
+ visual_chars Number of chars visually selected
+ (only in Visual mode)
+ visual_bytes Number of bytes visually selected
+ (only in Visual mode)
+ visual_words Number of chars visually selected
+ (only in Visual mode)
+
+
*writefile()*
writefile({list}, {fname} [, {flags}])
Write |List| {list} to file {fname}. Each list item is
diff --git a/runtime/doc/usr_41.txt b/runtime/doc/usr_41.txt
--- a/runtime/doc/usr_41.txt
+++ b/runtime/doc/usr_41.txt
@@ -918,6 +918,7 @@ Various: *various-functions*
mzeval() evaluate |MzScheme| expression
py3eval() evaluate Python expression (|+python3|)
pyeval() evaluate Python expression (|+python|)
+ wordcount() get byte/word/char count of buffer
==============================================================================
*41.7* Defining a function
diff --git a/src/eval.c b/src/eval.c
--- a/src/eval.c
+++ b/src/eval.c
@@ -776,6 +776,7 @@ static void f_winrestview __ARGS((typval
static void f_winsaveview __ARGS((typval_T *argvars, typval_T *rettv));
static void f_winwidth __ARGS((typval_T *argvars, typval_T *rettv));
static void f_writefile __ARGS((typval_T *argvars, typval_T *rettv));
+static void f_wordcount __ARGS((typval_T *argvars, typval_T *rettv));
static void f_xor __ARGS((typval_T *argvars, typval_T *rettv));
static int list2fpos __ARGS((typval_T *arg, pos_T *posp, int *fnump, colnr_T *curswantp));
@@ -8377,6 +8378,7 @@ static struct fst
{"winrestview", 1, 1, f_winrestview},
{"winsaveview", 0, 0, f_winsaveview},
{"winwidth", 1, 1, f_winwidth},
+ {"wordcount", 0, 0, f_wordcount},
{"writefile", 2, 3, f_writefile},
{"xor", 2, 2, f_xor},
};
@@ -20034,6 +20036,22 @@ f_winwidth(argvars, rettv)
}
/*
+ * "wordcount()" function
+ */
+ static void
+f_wordcount(argvars, rettv)
+ typval_T *argvars UNUSED;
+ typval_T *rettv;
+{
+ dict_T *dict;
+
+ if (rettv_dict_alloc(rettv) == FAIL)
+ return;
+ dict = rettv->vval.v_dict;
+ cursor_pos_info(dict);
+}
+
+/*
* Write list of strings to file
*/
static int
diff --git a/src/normal.c b/src/normal.c
--- a/src/normal.c
+++ b/src/normal.c
@@ -8267,7 +8267,7 @@ nv_g_cmd(cap)
* "g CTRL-G": display info about cursor position
*/
case Ctrl_G:
- cursor_pos_info();
+ cursor_pos_info(NULL);
break;
/*
diff --git a/src/ops.c b/src/ops.c
--- a/src/ops.c
+++ b/src/ops.c
@@ -6921,13 +6921,15 @@ line_count_info(line, wc, cc, limit, eol
* the *_count_cursor variables store running totals for the selection.)
*/
void
-cursor_pos_info()
+cursor_pos_info(dict)
+ dict_T *dict; /* do not print output, just return info for wordcount() function */
{
char_u *p;
char_u buf1[50];
char_u buf2[40];
linenr_T lnum;
long byte_count = 0;
+ long bom_count = 0;
long byte_count_cursor = 0;
long char_count = 0;
long char_count_cursor = 0;
@@ -6945,7 +6947,11 @@ cursor_pos_info()
*/
if (curbuf->b_ml.ml_flags & ML_EMPTY)
{
- MSG(_(no_lines_msg));
+ if (dict == NULL)
+ {
+ MSG(_(no_lines_msg));
+ return;
+ }
}
else
{
@@ -7078,74 +7084,98 @@ cursor_pos_info()
if (!curbuf->b_p_eol && (curbuf->b_p_bin || !curbuf->b_p_fixeol))
byte_count -= eol_size;
- if (VIsual_active)
+ if (dict == NULL)
{
- if (VIsual_mode == Ctrl_V && curwin->w_curswant < MAXCOL)
+ if (VIsual_active)
{
- getvcols(curwin, &min_pos, &max_pos, &min_pos.col,
- &max_pos.col);
- vim_snprintf((char *)buf1, sizeof(buf1), _("%ld Cols; "),
- (long)(oparg.end_vcol - oparg.start_vcol + 1));
+ if (VIsual_mode == Ctrl_V && curwin->w_curswant < MAXCOL)
+ {
+ getvcols(curwin, &min_pos, &max_pos, &min_pos.col,
+ &max_pos.col);
+ vim_snprintf((char *)buf1, sizeof(buf1), _("%ld Cols; "),
+ (long)(oparg.end_vcol - oparg.start_vcol + 1));
+ }
+ else
+ buf1[0] = NUL;
+
+ if (char_count_cursor == byte_count_cursor
+ && char_count == byte_count)
+ vim_snprintf((char *)IObuff, IOSIZE,
+ _("Selected %s%ld of %ld Lines; %ld of %ld Words; %ld of %ld Bytes"),
+ buf1, line_count_selected,
+ (long)curbuf->b_ml.ml_line_count,
+ word_count_cursor, word_count,
+ byte_count_cursor, byte_count);
+ else
+ vim_snprintf((char *)IObuff, IOSIZE,
+ _("Selected %s%ld of %ld Lines; %ld of %ld Words; %ld of %ld Chars; %ld of %ld Bytes"),
+ buf1, line_count_selected,
+ (long)curbuf->b_ml.ml_line_count,
+ word_count_cursor, word_count,
+ char_count_cursor, char_count,
+ byte_count_cursor, byte_count);
}
else
- buf1[0] = NUL;
-
- if (char_count_cursor == byte_count_cursor
- && char_count == byte_count)
- vim_snprintf((char *)IObuff, IOSIZE,
- _("Selected %s%ld of %ld Lines; %ld of %ld Words; %ld of %ld Bytes"),
- buf1, line_count_selected,
+ {
+ p = ml_get_curline();
+ validate_virtcol();
+ col_print(buf1, sizeof(buf1), (int)curwin->w_cursor.col + 1,
+ (int)curwin->w_virtcol + 1);
+ col_print(buf2, sizeof(buf2), (int)STRLEN(p),
+ linetabsize(p));
+
+ if (char_count_cursor == byte_count_cursor
+ && char_count == byte_count)
+ vim_snprintf((char *)IObuff, IOSIZE,
+ _("Col %s of %s; Line %ld of %ld; Word %ld of %ld; Byte %ld of %ld"),
+ (char *)buf1, (char *)buf2,
+ (long)curwin->w_cursor.lnum,
(long)curbuf->b_ml.ml_line_count,
word_count_cursor, word_count,
byte_count_cursor, byte_count);
- else
- vim_snprintf((char *)IObuff, IOSIZE,
- _("Selected %s%ld of %ld Lines; %ld of %ld Words; %ld of %ld Chars; %ld of %ld Bytes"),
- buf1, line_count_selected,
+ else
+ vim_snprintf((char *)IObuff, IOSIZE,
+ _("Col %s of %s; Line %ld of %ld; Word %ld of %ld; Char %ld of %ld; Byte %ld of %ld"),
+ (char *)buf1, (char *)buf2,
+ (long)curwin->w_cursor.lnum,
(long)curbuf->b_ml.ml_line_count,
word_count_cursor, word_count,
char_count_cursor, char_count,
byte_count_cursor, byte_count);
+ }
+ }
+
+ /* Don't shorten this message, the user asked for it. */
+#ifdef FEAT_MBYTE
+ bom_count = bomb_size();
+ if (bom_count > 0)
+ sprintf((char *)IObuff + STRLEN(IObuff), _("(+%ld for BOM)"),
+ bom_count);
+#endif
+ if (dict == NULL)
+ {
+ p = p_shm;
+ p_shm = (char_u *)"";
+ msg(IObuff);
+ p_shm = p;
+ }
+ }
+ if (dict != NULL)
+ {
+ dict_add_nr_str(dict, "words", (long)word_count, NULL);
+ dict_add_nr_str(dict, "chars", (long)char_count, NULL);
+ dict_add_nr_str(dict, "bytes", (long)byte_count + bom_count, NULL);
+ if (VIsual_active)
+ {
+ dict_add_nr_str(dict, "visual_bytes", (long)byte_count_cursor, NULL);
+ dict_add_nr_str(dict, "visual_chars", (long)char_count_cursor, NULL);
+ dict_add_nr_str(dict, "visual_words", (long)word_count_cursor, NULL);
}
else
{
- p = ml_get_curline();
- validate_virtcol();
- col_print(buf1, sizeof(buf1), (int)curwin->w_cursor.col + 1,
- (int)curwin->w_virtcol + 1);
- col_print(buf2, sizeof(buf2), (int)STRLEN(p),
- linetabsize(p));
-
- if (char_count_cursor == byte_count_cursor
- && char_count == byte_count)
- vim_snprintf((char *)IObuff, IOSIZE,
- _("Col %s of %s; Line %ld of %ld; Word %ld of %ld; Byte %ld of %ld"),
- (char *)buf1, (char *)buf2,
- (long)curwin->w_cursor.lnum,
- (long)curbuf->b_ml.ml_line_count,
- word_count_cursor, word_count,
- byte_count_cursor, byte_count);
- else
- vim_snprintf((char *)IObuff, IOSIZE,
- _("Col %s of %s; Line %ld of %ld; Word %ld of %ld; Char %ld of %ld; Byte %ld of %ld"),
- (char *)buf1, (char *)buf2,
- (long)curwin->w_cursor.lnum,
- (long)curbuf->b_ml.ml_line_count,
- word_count_cursor, word_count,
- char_count_cursor, char_count,
- byte_count_cursor, byte_count);
+ dict_add_nr_str(dict, "cursor_bytes", (long)byte_count_cursor, NULL);
+ dict_add_nr_str(dict, "cursor_chars", (long)char_count_cursor, NULL);
+ dict_add_nr_str(dict, "cursor_words", (long)word_count_cursor, NULL);
}
-
-#ifdef FEAT_MBYTE
- byte_count = bomb_size();
- if (byte_count > 0)
- sprintf((char *)IObuff + STRLEN(IObuff), _("(+%ld for BOM)"),
- byte_count);
-#endif
- /* Don't shorten this message, the user asked for it. */
- p = p_shm;
- p_shm = (char_u *)"";
- msg(IObuff);
- p_shm = p;
}
}
diff --git a/src/proto/ops.pro b/src/proto/ops.pro
--- a/src/proto/ops.pro
+++ b/src/proto/ops.pro
@@ -58,5 +58,5 @@ void write_reg_contents __ARGS((int name
void write_reg_contents_lst __ARGS((int name, char_u **strings, int maxlen, int must_append, int yank_type, long block_len));
void write_reg_contents_ex __ARGS((int name, char_u *str, int maxlen, int must_append, int yank_type, long block_len));
void clear_oparg __ARGS((oparg_T *oap));
-void cursor_pos_info __ARGS((void));
+void cursor_pos_info __ARGS((dict_T *eval));
/* vim: set ft=c : */
diff --git a/src/testdir/Make_amiga.mak b/src/testdir/Make_amiga.mak
--- a/src/testdir/Make_amiga.mak
+++ b/src/testdir/Make_amiga.mak
@@ -68,7 +68,8 @@ SCRIPTS = test1.out test3.out test4.out
test_signs.out \
test_tagcase.out \
test_textobjects.out \
- test_utf8.out
+ test_utf8.out \
+ test_wordcount.out
.SUFFIXES: .in .out
@@ -225,3 +226,4 @@ test_signs.out: test_signs.in
test_tagcase.out: test_tagcase.in
test_textobjects.out: test_textobjects.in
test_utf8.out: test_utf8.in
+test_wordcount.out: test_wordcount.in
diff --git a/src/testdir/Make_dos.mak b/src/testdir/Make_dos.mak
--- a/src/testdir/Make_dos.mak
+++ b/src/testdir/Make_dos.mak
@@ -67,7 +67,8 @@ SCRIPTS = test3.out test4.out test5.out
test_signs.out \
test_tagcase.out \
test_textobjects.out \
- test_utf8.out
+ test_utf8.out \
+ test_wordcount.out
SCRIPTS32 = test50.out test70.out
diff --git a/src/testdir/Make_ming.mak b/src/testdir/Make_ming.mak
--- a/src/testdir/Make_ming.mak
+++ b/src/testdir/Make_ming.mak
@@ -89,7 +89,8 @@ SCRIPTS = test3.out test4.out test5.out
test_signs.out \
test_tagcase.out \
test_textobjects.out \
- test_utf8.out
+ test_utf8.out \
+ test_wordcount.out
SCRIPTS32 = test50.out test70.out
diff --git a/src/testdir/Make_os2.mak b/src/testdir/Make_os2.mak
--- a/src/testdir/Make_os2.mak
+++ b/src/testdir/Make_os2.mak
@@ -69,7 +69,8 @@ SCRIPTS = test1.out test3.out test4.out
test_signs.out \
test_tagcase.out \
test_textobjects.out \
- test_utf8.out
+ test_utf8.out \
+ test_wordcount.out
SCRIPTS_BENCH = bench_re_freeze.out
diff --git a/src/testdir/Make_vms.mms b/src/testdir/Make_vms.mms
--- a/src/testdir/Make_vms.mms
+++ b/src/testdir/Make_vms.mms
@@ -128,7 +128,8 @@ SCRIPT = test1.out test2.out test3.out
test_signs.out \
test_tagcase.out \
test_textobjects.out \
- test_utf8.out
+ test_utf8.out \
+ test_wordcount.out
# Known problems:
# test17: ?
diff --git a/src/testdir/Makefile b/src/testdir/Makefile
--- a/src/testdir/Makefile
+++ b/src/testdir/Makefile
@@ -65,7 +65,8 @@ SCRIPTS = test1.out test2.out test3.out
test_signs.out \
test_tagcase.out \
test_textobjects.out \
- test_utf8.out
+ test_utf8.out \
+ teset_wordcount.out
SCRIPTS_GUI = test16.out
diff --git a/src/testdir/test_wordcount.in b/src/testdir/test_wordcount.in
new file mode 100644
--- /dev/null
+++ b/src/testdir/test_wordcount.in
@@ -0,0 +1,125 @@
+Test for wordcount() function
+
+STARTTEST
+:so small.vim
+:so mbyte.vim
+:set enc=utf8
+:new
+:fu DoRecordWin(...)
+: wincmd k
+: if exists("a:1")
+: call cursor(a:1)
+: endif
+: let result=[]
+: call add(result, g:test)
+: call add(result, getline(1, '$'))
+: call add(result, wordcount())
+: wincmd j
+: return result
+:endfu
+:fu PutInWindow(args)
+: wincmd k
+: %d _
+: call append(1, a:args)
+: wincmd j
+:endfu
+:fu Log()
+: $put ='----'
+: $put =remove(g:log,0)
+: $put =string(g:log)
+:endfu
+:fu! STL()
+: if mode() =~? 'V'
+: let g:visual_stat=wordcount()
+: endif
+: return string(wordcount())
+:endfu
+:let g:test="Test 1: empty window"
+:let log=DoRecordWin()
+:call Log()
+:"
+:let g:test="Test 2: some words, cursor at start"
+:call PutInWindow('one two three')
+:let log=DoRecordWin([1,1,0])
+:call Log()
+:"
+:let g:test="Test 3: some words, cursor at end"
+:call PutInWindow('one two three')
+:let log=DoRecordWin([2,99,0])
+:call Log()
+:"
+:let g:test="Test 4: some words, cursor at end, ve=all"
+:set ve=all
+:call PutInWindow('one two three')
+:let log=DoRecordWin([2,99,0])
+:call Log()
+:set ve=
+:"
+:let g:test="Test 5: several lines with words"
+:call PutInWindow(['one two three', 'one two three', 'one two three'])
+:let log=DoRecordWin([4,99,0])
+:call Log()
+:"
+:let g:test="Test 6: one line with BOM set"
+:call PutInWindow('one two three')
+:wincmd k
+:set bomb
+:w! Xtest
+:wincmd j
+:let log=DoRecordWin([2,99,0])
+:call Log()
+:wincmd k
+:set nobomb
+:w!
+:wincmd j
+:"
+:let g:test="Test 7: one line with multibyte words"
+:call PutInWindow(['Ãne Mäne Müh'])
+:let log=DoRecordWin([2,99,0])
+:call Log()
+:"
+:let g:test="Test 8: several lines with multibyte words"
+:call PutInWindow(['Ãne Mäne Müh', 'und raus bist dü!'])
+:let log=DoRecordWin([3,99,0])
+:call Log()
+:"
+:let g:test="Test 9: visual mode, complete buffer"
+:call PutInWindow(['Ãne Mäne Müh', 'und raus bist dü!'])
+:wincmd k
+:set ls=2 stl=%{STL()}
+:" start visual mode quickly and select complete buffer
+:0
+V2jy
+:set stl= ls=1
+:let log=DoRecordWin([3,99,0])
+:let log[2]=g:visual_stat
+:call Log()
+:"
+:let g:test="Test 10: visual mode (empty)"
+:call PutInWindow(['Ãne Mäne Müh', 'und raus bist dü!'])
+:wincmd k
+:set ls=2 stl=%{STL()}
+:" start visual mode quickly and select complete buffer
+:0
+v$y
+:set stl= ls=1
+:let log=DoRecordWin([3,99,0])
+:let log[2]=g:visual_stat
+:call Log()
+:"
+:let g:test="Test 11: visual mode, single line"
+:call PutInWindow(['Ãne Mäne Müh', 'und raus bist dü!'])
+:wincmd k
+:set ls=2 stl=%{STL()}
+:" start visual mode quickly and select complete buffer
+:2
+0v$y
+:set stl= ls=1
+:let log=DoRecordWin([3,99,0])
+:let log[2]=g:visual_stat
+:call Log()
+:"
+:/^RESULT test/,$w! test.out
+:qa!
+ENDTEST
+RESULT test:
diff --git a/src/testdir/test_wordcount.ok b/src/testdir/test_wordcount.ok
new file mode 100644
--- /dev/null
+++ b/src/testdir/test_wordcount.ok
@@ -0,0 +1,34 @@
+RESULT test:
+----
+Test 1: empty window
+[[''], {'chars': 0, 'cursor_chars': 0, 'words': 0, 'cursor_words': 0, 'bytes': 0, 'cursor_bytes': 0}]
+----
+Test 2: some words, cursor at start
+[['', 'one two three'], {'chars': 15, 'cursor_chars': 1, 'words': 3, 'cursor_words': 0, 'bytes': 15, 'cursor_bytes': 1}]
+----
+Test 3: some words, cursor at end
+[['', 'one two three'], {'chars': 15, 'cursor_chars': 14, 'words': 3, 'cursor_words': 3, 'bytes': 15, 'cursor_bytes': 14}]
+----
+Test 4: some words, cursor at end, ve=all
+[['', 'one two three'], {'chars': 15, 'cursor_chars': 15, 'words': 3, 'cursor_words': 3, 'bytes': 15, 'cursor_bytes': 15}]
+----
+Test 5: several lines with words
+[['', 'one two three', 'one two three', 'one two three'], {'chars': 43, 'cursor_chars': 42, 'words': 9, 'cursor_words': 9, 'bytes': 43, 'cursor_bytes': 42}]
+----
+Test 6: one line with BOM set
+[['', 'one two three'], {'chars': 15, 'cursor_chars': 14, 'words': 3, 'cursor_words': 3, 'bytes': 18, 'cursor_bytes': 14}]
+----
+Test 7: one line with multibyte words
+[['', 'Ãne Mäne Müh'], {'chars': 14, 'cursor_chars': 13, 'words': 3, 'cursor_words': 3, 'bytes': 17, 'cursor_bytes': 16}]
+----
+Test 8: several lines with multibyte words
+[['', 'Ãne Mäne Müh', 'und raus bist dü!'], {'chars': 32, 'cursor_chars': 31, 'words': 7, 'cursor_words': 7, 'bytes': 36, 'cursor_bytes': 35}]
+----
+Test 9: visual mode, complete buffer
+[['', 'Ãne Mäne Müh', 'und raus bist dü!'], {'chars': 32, 'words': 7, 'bytes': 36, 'visual_chars': 32, 'visual_words': 7, 'visual_bytes': 36}]
+----
+Test 10: visual mode (empty)
+[['', 'Ãne Mäne Müh', 'und raus bist dü!'], {'chars': 32, 'words': 7, 'bytes': 36, 'visual_chars': 1, 'visual_words': 0, 'visual_bytes': 1}]
+----
+Test 11: visual mode, single line
+[['', 'Ãne Mäne Müh', 'und raus bist dü!'], {'chars': 32, 'words': 7, 'bytes': 36, 'visual_chars': 13, 'visual_words': 3, 'visual_bytes': 16}]
