Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
W
WCCL
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Redmine
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
GitLab community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Analysers
WCCL
Commits
e43767e1
Commit
e43767e1
authored
Aug 22, 2011
by
Lukasz Bilenkij
Browse files
Options
Downloads
Patches
Plain Diff
mwefile-list handling
parent
917e75bc
No related branches found
No related tags found
No related merge requests found
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
libmwereader/mwereader.cpp
+29
-2
29 additions, 2 deletions
libmwereader/mwereader.cpp
libmwereader/mwereader.h
+4
-0
4 additions, 0 deletions
libmwereader/mwereader.h
with
33 additions
and
2 deletions
libmwereader/mwereader.cpp
+
29
−
2
View file @
e43767e1
#include
"mwereader.h"
#include
"mweparser.h"
#include
<boost/algorithm/string.hpp>
#include
<boost/filesystem.hpp>
namespace
Corpus2
{
...
...
@@ -11,7 +12,7 @@ bool MWEReader::registered = TokenReader::register_path_reader<MWEReader>(
MWEReader
::
MWEReader
(
const
Tagset
&
tagset
,
const
std
::
string
&
filename
)
:
TokenReader
(
tagset
),
inner_filename_
(
filename
)
{
// TODO implementataion?
mwes_counter
=
0
;
}
MWEReader
::~
MWEReader
()
...
...
@@ -156,8 +157,30 @@ bool MWEReader::registered = TokenReader::register_path_reader<MWEReader>(
currentSentence
=
boost
::
make_shared
<
Sentence
>
();
}
if
(
boost
::
algorithm
::
starts_with
(
option
,
"mwefile:"
))
{
std
::
string
mwefile
=
option
.
substr
(
8
);
if
(
boost
::
filesystem
::
exists
(
mwefile
))
load_mwes
(
mwefile
);
else
throw
std
::
runtime_error
(
"File "
+
mwefile
+
" does not exists"
);
}
if
(
boost
::
algorithm
::
starts_with
(
option
,
"mwefile-list:"
))
{
std
::
string
mwefile
=
option
.
substr
(
13
);
size_t
found
=
mwefile
.
find
(
" "
,
0
);
while
(
found
!=
std
::
string
::
npos
)
{
std
::
string
file
=
mwefile
.
substr
(
0
,
found
);
if
(
boost
::
filesystem
::
exists
(
file
))
load_mwes
(
file
);
else
throw
std
::
runtime_error
(
"File "
+
mwefile
+
" does not exists"
);
mwefile
=
mwefile
.
substr
(
found
+
1
);
found
=
mwefile
.
find
(
" "
,
0
);
}
if
(
boost
::
filesystem
::
exists
(
mwefile
))
load_mwes
(
mwefile
);
else
throw
std
::
runtime_error
(
"File "
+
mwefile
+
" does not exists"
);
}
...
...
@@ -166,8 +189,11 @@ bool MWEReader::registered = TokenReader::register_path_reader<MWEReader>(
void
MWEReader
::
validate
()
{
if
(
inner_reader_
==
NULL
)
throw
Corpus2Error
(
"Inner reader not initialised."
);
if
(
mwes_counter
==
0
)
throw
Corpus2Error
(
"MWE files were not loaded"
);
// TODO MWE stuff
}
...
...
@@ -184,6 +210,7 @@ bool MWEReader::registered = TokenReader::register_path_reader<MWEReader>(
{
MWEParser
parser
(
mwe_index_
);
parser
.
parse_file
(
filename
);
mwes_counter
++
;
}
...
...
This diff is collapsed.
Click to expand it.
libmwereader/mwereader.h
+
4
−
0
View file @
e43767e1
...
...
@@ -63,8 +63,12 @@ private:
std
::
string
inner_filename_
;
/// inner reader option
size_t
token_index
;
/// contains last processed sentence
Sentence
::
Ptr
currentSentence
;
/// contains last processed chunk
boost
::
shared_ptr
<
Chunk
>
currentChunk
;
/// quantity of loaded mwes files
size_t
mwes_counter
;
};
}
// ns Corpus2
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
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