Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
C
corpus2
Manage
Activity
Members
Labels
Plan
Issues
4
Issue boards
Milestones
Wiki
Redmine
Code
Merge requests
0
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container Registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Analysers
corpus2
Commits
ed68caee
Commit
ed68caee
authored
13 years ago
by
dominik
Browse files
Options
Downloads
Patches
Plain Diff
conllwriter added
parent
89d0bbf8
No related merge requests found
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
libcorpus2/CMakeLists.txt
+1
-0
1 addition, 0 deletions
libcorpus2/CMakeLists.txt
libcorpus2/io/conllwriter.cpp
+71
-0
71 additions, 0 deletions
libcorpus2/io/conllwriter.cpp
libcorpus2/io/conllwriter.h
+35
-0
35 additions, 0 deletions
libcorpus2/io/conllwriter.h
with
107 additions
and
0 deletions
libcorpus2/CMakeLists.txt
+
1
−
0
View file @
ed68caee
...
...
@@ -53,6 +53,7 @@ SET(libcorpus2_STAT_SRC
tokenmetadata.cpp
io/cclreader.cpp
io/cclwriter.cpp
io/conllwriter.cpp
io/helpers.cpp
io/fastxces.cpp
io/iob-chan.cpp
...
...
This diff is collapsed.
Click to expand it.
libcorpus2/io/conllwriter.cpp
0 → 100644
+
71
−
0
View file @
ed68caee
#include
"conllwriter.h"
#include
<libpwrutils/foreach.h>
#include
<boost/algorithm/string.hpp>
namespace
Corpus2
{
bool
ConllWriter
::
registered
=
TokenWriter
::
register_writer
<
ConllWriter
>
(
"conll"
);
ConllWriter
::
ConllWriter
(
std
::
ostream
&
os
,
const
Tagset
&
tagset
,
const
string_range_vector
&
params
)
:
TokenWriter
(
os
,
tagset
,
params
)
{
myTagset
=
tagset
;
}
ConllWriter
::~
ConllWriter
()
{
finish
();
}
void
ConllWriter
::
write_token
(
const
Token
&
t
)
{
os
()
<<
t
.
orth_utf8
()
<<
"
\t
"
;
Lexeme
lex
=
t
.
get_preferred_lexeme
(
myTagset
);
os
()
<<
lex
.
lemma_utf8
()
+
"
\t
"
;
std
::
string
tag
=
myTagset
.
tag_to_string
(
lex
.
tag
());
std
::
vector
<
std
::
string
>
strs
;
boost
::
split
(
strs
,
tag
,
boost
::
is_any_of
(
":"
));
os
()
<<
strs
[
0
]
<<
"
\t
"
<<
strs
[
0
]
<<
"
\t
"
;
if
(
strs
.
size
()
>
1
)
{
size_t
i
;
for
(
i
=
1
;
i
<
strs
.
size
()
-
1
;
i
++
)
{
os
()
<<
strs
[
i
]
<<
"|"
;
}
os
()
<<
strs
[
i
]
<<
"
\t
_
\t
_
\t
_
\t
_"
;
}
else
os
()
<<
"_
\t
_
\t
_
\t
_
\t
_"
;
}
void
ConllWriter
::
write_sentence
(
const
Sentence
&
s
)
{
int
i
=
1
;
foreach
(
const
Token
*
t
,
s
.
tokens
())
{
os
()
<<
i
<<
"
\t
"
;
write_token
(
*
t
);
os
()
<<
"
\n
"
;
i
++
;
}
}
void
ConllWriter
::
write_chunk
(
const
Chunk
&
c
)
{
foreach
(
const
Sentence
::
ConstPtr
&
s
,
c
.
sentences
())
{
write_sentence
(
*
s
);
}
}
void
ConllWriter
::
do_header
()
{
}
void
ConllWriter
::
do_footer
()
{
}
}
/* end ns Corpus2 */
This diff is collapsed.
Click to expand it.
libcorpus2/io/conllwriter.h
0 → 100644
+
35
−
0
View file @
ed68caee
#ifndef CONLLWRITER_H
#define CONLLWRITER_H
#include
<libcorpus2/io/writer.h>
namespace
Corpus2
{
class
ConllWriter
:
public
TokenWriter
{
public:
ConllWriter
(
std
::
ostream
&
os
,
const
Tagset
&
tagset
,
const
string_range_vector
&
params
);
~
ConllWriter
();
void
write_token
(
const
Token
&
t
);
void
write_sentence
(
const
Sentence
&
s
);
void
write_chunk
(
const
Chunk
&
c
);
static
bool
registered
;
protected:
void
do_header
();
void
do_footer
();
private:
Tagset
myTagset
;
};
}
/* end ns Corpus2 */
#endif // CONLLWRITER_H
This diff is collapsed.
Click to expand it.
Preview
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment