summaryrefslogtreecommitdiff
path: root/klm/lm/query_main.cc
diff options
context:
space:
mode:
authorarmatthews <armatthe@cmu.edu>2014-10-13 14:59:23 -0400
committerarmatthews <armatthe@cmu.edu>2014-10-13 14:59:23 -0400
commitb26cda84e05d4523eee069234a975a0153bf8608 (patch)
tree61c9da4f8dd6070f27c8e81812a76fc0a8cf2d8d /klm/lm/query_main.cc
parentcd7bc67f475fdfd07fba003ac4cca40e83944740 (diff)
parentb1ed81ef3216b212295afa76c5d20a56fb647204 (diff)
Merge branch 'master' of github.com:redpony/cdec
Diffstat (limited to 'klm/lm/query_main.cc')
-rw-r--r--klm/lm/query_main.cc75
1 files changed, 54 insertions, 21 deletions
diff --git a/klm/lm/query_main.cc b/klm/lm/query_main.cc
index bd4fde62..3013ff21 100644
--- a/klm/lm/query_main.cc
+++ b/klm/lm/query_main.cc
@@ -1,4 +1,5 @@
#include "lm/ngram_query.hh"
+#include "util/getopt.hh"
#ifdef WITH_NPLM
#include "lm/wrappers/nplm.hh"
@@ -7,47 +8,76 @@
#include <stdlib.h>
void Usage(const char *name) {
- std::cerr << "KenLM was compiled with maximum order " << KENLM_MAX_ORDER << "." << std::endl;
- std::cerr << "Usage: " << name << " [-n] lm_file" << std::endl;
- std::cerr << "Input is wrapped in <s> and </s> unless -n is passed." << std::endl;
+ std::cerr <<
+ "KenLM was compiled with maximum order " << KENLM_MAX_ORDER << ".\n"
+ "Usage: " << name << " [-n] [-s] lm_file\n"
+ "-n: Do not wrap the input in <s> and </s>.\n"
+ "-s: Sentence totals only.\n"
+ "-l lazy|populate|read|parallel: Load lazily, with populate, or malloc+read\n"
+ "The default loading method is populate on Linux and read on others.\n";
exit(1);
}
int main(int argc, char *argv[]) {
+ if (argc == 1 || (argc == 2 && !strcmp(argv[1], "--help")))
+ Usage(argv[0]);
+
+ lm::ngram::Config config;
bool sentence_context = true;
- const char *file = NULL;
- for (char **arg = argv + 1; arg != argv + argc; ++arg) {
- if (!strcmp(*arg, "-n")) {
- sentence_context = false;
- } else if (!strcmp(*arg, "-h") || !strcmp(*arg, "--help") || file) {
- Usage(argv[0]);
- } else {
- file = *arg;
+ bool show_words = true;
+
+ int opt;
+ while ((opt = getopt(argc, argv, "hnsl:")) != -1) {
+ switch (opt) {
+ case 'n':
+ sentence_context = false;
+ break;
+ case 's':
+ show_words = false;
+ break;
+ case 'l':
+ if (!strcmp(optarg, "lazy")) {
+ config.load_method = util::LAZY;
+ } else if (!strcmp(optarg, "populate")) {
+ config.load_method = util::POPULATE_OR_READ;
+ } else if (!strcmp(optarg, "read")) {
+ config.load_method = util::READ;
+ } else if (!strcmp(optarg, "parallel")) {
+ config.load_method = util::PARALLEL_READ;
+ } else {
+ Usage(argv[0]);
+ }
+ break;
+ case 'h':
+ default:
+ Usage(argv[0]);
}
}
- if (!file) Usage(argv[0]);
+ if (optind + 1 != argc)
+ Usage(argv[0]);
+ const char *file = argv[optind];
try {
using namespace lm::ngram;
ModelType model_type;
if (RecognizeBinary(file, model_type)) {
switch(model_type) {
case PROBING:
- Query<lm::ngram::ProbingModel>(file, sentence_context, std::cin, std::cout);
+ Query<lm::ngram::ProbingModel>(file, config, sentence_context, show_words);
break;
case REST_PROBING:
- Query<lm::ngram::RestProbingModel>(file, sentence_context, std::cin, std::cout);
+ Query<lm::ngram::RestProbingModel>(file, config, sentence_context, show_words);
break;
case TRIE:
- Query<TrieModel>(file, sentence_context, std::cin, std::cout);
+ Query<TrieModel>(file, config, sentence_context, show_words);
break;
case QUANT_TRIE:
- Query<QuantTrieModel>(file, sentence_context, std::cin, std::cout);
+ Query<QuantTrieModel>(file, config, sentence_context, show_words);
break;
case ARRAY_TRIE:
- Query<ArrayTrieModel>(file, sentence_context, std::cin, std::cout);
+ Query<ArrayTrieModel>(file, config, sentence_context, show_words);
break;
case QUANT_ARRAY_TRIE:
- Query<QuantArrayTrieModel>(file, sentence_context, std::cin, std::cout);
+ Query<QuantArrayTrieModel>(file, config, sentence_context, show_words);
break;
default:
std::cerr << "Unrecognized kenlm model type " << model_type << std::endl;
@@ -56,12 +86,15 @@ int main(int argc, char *argv[]) {
#ifdef WITH_NPLM
} else if (lm::np::Model::Recognize(file)) {
lm::np::Model model(file);
- Query(model, sentence_context, std::cin, std::cout);
+ if (show_words) {
+ Query<lm::np::Model, lm::ngram::FullPrint>(model, sentence_context);
+ } else {
+ Query<lm::np::Model, lm::ngram::BasicPrint>(model, sentence_context);
+ }
#endif
} else {
- Query<ProbingModel>(file, sentence_context, std::cin, std::cout);
+ Query<ProbingModel>(file, config, sentence_context, show_words);
}
- std::cerr << "Total time including destruction:\n";
util::PrintUsage(std::cerr);
} catch (const std::exception &e) {
std::cerr << e.what() << std::endl;