diff options
| author | Kelly Rauchenberger <fefferburbia@gmail.com> | 2016-02-14 12:17:47 -0500 |
|---|---|---|
| committer | Kelly Rauchenberger <fefferburbia@gmail.com> | 2016-02-14 12:17:47 -0500 |
| commit | 1756b9ee3f985365b339706d972e8a2ee14c3ef5 (patch) | |
| tree | 0e788370a6e2934a241cb15b42942e01b16bec73 | |
| parent | 1971f4936b53bc05765b88a2c76e675a18555237 (diff) | |
| download | rawr-ebooks-1756b9ee3f985365b339706d972e8a2ee14c3ef5.tar.gz rawr-ebooks-1756b9ee3f985365b339706d972e8a2ee14c3ef5.tar.bz2 rawr-ebooks-1756b9ee3f985365b339706d972e8a2ee14c3ef5.zip | |
Fixed incorrect diversity of tokens containing the letters aemnou
| -rw-r--r-- | kgramstats.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
| diff --git a/kgramstats.cpp b/kgramstats.cpp index f78336e..af24606 100644 --- a/kgramstats.cpp +++ b/kgramstats.cpp | |||
| @@ -162,7 +162,7 @@ kgramstats::kgramstats(std::string corpus, int maxK) | |||
| 162 | { | 162 | { |
| 163 | if ( | 163 | if ( |
| 164 | // Legacy freevars should be distinct from tokens containing similar words | 164 | // Legacy freevars should be distinct from tokens containing similar words |
| 165 | (canonical.find_first_of("$name$") != std::string::npos) || (canonical.find_first_of("$noun$") != std::string::npos) | 165 | (canonical.find("$name$") != std::string::npos) || (canonical.find("$noun$") != std::string::npos) |
| 166 | // Words with no letters will be mangled by the spell checker | 166 | // Words with no letters will be mangled by the spell checker |
| 167 | || (canonical.find_first_of("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz") == std::string::npos) | 167 | || (canonical.find_first_of("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz") == std::string::npos) |
| 168 | ) | 168 | ) |