diff options
author | Feffernoose <fefferburbia@gmail.com> | 2013-10-06 15:03:29 -0400 |
---|---|---|
committer | Feffernoose <fefferburbia@gmail.com> | 2013-10-06 15:03:29 -0400 |
commit | 8e2693ebb6670f8b8c66f5818be87140467ed5f3 (patch) | |
tree | 6f78c3cd5cee959fbed0101ea96531513bfadb93 | |
parent | eb076ca2c6c8932fd251419563cf0078c5ee0914 (diff) | |
download | rawr-ebooks-8e2693ebb6670f8b8c66f5818be87140467ed5f3.tar.gz rawr-ebooks-8e2693ebb6670f8b8c66f5818be87140467ed5f3.tar.bz2 rawr-ebooks-8e2693ebb6670f8b8c66f5818be87140467ed5f3.zip |
Stripped empty tokens from corpus
-rw-r--r-- | kgramstats.cpp | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/kgramstats.cpp b/kgramstats.cpp index 6c0e4ce..327752b 100644 --- a/kgramstats.cpp +++ b/kgramstats.cpp | |||
@@ -4,6 +4,8 @@ | |||
4 | #include <cstdlib> | 4 | #include <cstdlib> |
5 | #include <algorithm> | 5 | #include <algorithm> |
6 | 6 | ||
7 | // runs in O(t^2) time where t is the number of tokens in the input corpus | ||
8 | // We consider maxK to be fairly constant | ||
7 | kgramstats::kgramstats(string corpus, int maxK) | 9 | kgramstats::kgramstats(string corpus, int maxK) |
8 | { | 10 | { |
9 | this->maxK = maxK; | 11 | this->maxK = maxK; |
@@ -16,7 +18,11 @@ kgramstats::kgramstats(string corpus, int maxK) | |||
16 | { | 18 | { |
17 | end = corpus.find(" ", start); | 19 | end = corpus.find(" ", start); |
18 | 20 | ||
19 | tokens.push_back(corpus.substr(start, (end == string::npos) ? string::npos : end - start)); | 21 | string token = corpus.substr(start, (end == string::npos) ? string::npos : end - start); |
22 | if (token.compare("")) | ||
23 | { | ||
24 | tokens.push_back(token); | ||
25 | } | ||
20 | 26 | ||
21 | start = ((end > (string::npos - 1) ) ? string::npos : end + 1); | 27 | start = ((end > (string::npos - 1) ) ? string::npos : end + 1); |
22 | } | 28 | } |
@@ -85,9 +91,9 @@ void printKgram(kgram k) | |||
85 | { | 91 | { |
86 | cout << *it << " "; | 92 | cout << *it << " "; |
87 | } | 93 | } |
88 | cout << endl; | ||
89 | } | 94 | } |
90 | 95 | ||
96 | // runs in O(n log t) time where n is the input number of sentences and t is the number of tokens in the input corpus | ||
91 | vector<string> kgramstats::randomSentence(int n) | 97 | vector<string> kgramstats::randomSentence(int n) |
92 | { | 98 | { |
93 | vector<string> result; | 99 | vector<string> result; |