Skip to content

count quantities with mecab japanese #149

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
HugoFara merged 3 commits into from
Dec 26, 2023
Merged

count quantities with mecab japanese #149

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ddbdfa9
count quantities with mecab japanese
ProgramComputer Oct 3, 2023
429d0b0
Update database_connect.php
ProgramComputer Oct 3, 2023
2647396
Merge branch 'dev' into patch-3
HugoFara Dec 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 21 additions & 3 deletions inc/database_connect.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -620,8 +620,9 @@ function update_japanese_word_count($japid)
$row = fgets($handle, 1024);
$arr = explode("4\t", $row, 2);
if (!empty($arr[1])) {
//TODO Add tests
$cnt = substr_count(
preg_replace('$[^267]\t$u', '', $arr[1]),
preg_replace('$[^2678]\t$u', '', $arr[1]),
"\t"
);
if (empty($cnt)) {
Expand Down Expand Up @@ -790,6 +791,7 @@ function parse_japanese_text($text, $id): ?array
);
$handle = fopen($file_name, 'r');
$mecabed = fread($handle, filesize($file_name));

fclose($handle);
$values = array();
$order = 0;
Expand All @@ -801,6 +803,7 @@ function parse_japanese_text($text, $id): ?array
);
}
$term_type = 0;
$last_node_type = 0;
$count = 0;
$row = array(0, 0, 0, "", 0);
foreach (explode(PHP_EOL, $mecabed) as $line) {
Expand All @@ -817,17 +820,32 @@ function parse_japanese_text($text, $id): ?array
$term = '¶';
}
$term_type = 2;
} else if (in_array($node_type, ['2', '6', '7'])) {
} else if (in_array($node_type, ['2', '6', '7', '8'])) {
$term_type = 0;
} else {
$term_type = 1;
}


$order += (int)(($term_type == 0) && ($last_term_type == 0)) +
(int)!(($term_type == 1) && ($last_term_type == 1));
$row[2] = $order; // TiOrder
$row[3] = convert_string_to_sqlsyntax_notrim_nonull($term); // TiText
$row[4] = $term_type == 0 ? 1 : 0; // TiWordCount
$values[] = "(" . implode(",", $row) . ")";
$values[] = $row;
if($last_node_type == 8 && $node_type == 8)
{
$lastKey = array_key_last($values);
if ($lastKey !== null) {
$values[$lastKey-1][3] = convert_string_to_sqlsyntax_notrim_nonull(str_replace("'", '', $values[$lastKey-1][3]).$term);
}
array_pop($values);
}
$last_node_type = $node_type;

}
foreach ($values as &$value) {
$value = "(" . implode(",", $value) . ")";
}
do_mysqli_query(
"INSERT INTO temptextitems2 (
Expand Down
4 changes: 2 additions & 2 deletions inc/session_utility.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3695,9 +3695,9 @@ function sentences_containing_word_lc_query($wordlc, $lid): string
if (!feof($handle)) {
$row = fgets($handle, 256);
// Format string removing numbers.
// MeCab tip: 2 = hiragana, 6 = kanji, 7 = katakana
// MeCab tip: 2 = hiragana, 6 = kanji, 7 = katakana, 8 = kazu
$mecab_str = "\t" . preg_replace_callback(
'([267]?)\t[0-9]+$',
'([2678]?)\t[0-9]+$',
function ($matches) {
return isset($matches[1]) ? "\t" : "";
},
Expand Down