diff options
Diffstat (limited to 'src/backend/tsearch')
-rw-r--r-- | src/backend/tsearch/ts_locale.c | 4 | ||||
-rw-r--r-- | src/backend/tsearch/ts_typanalyze.c | 14 | ||||
-rw-r--r-- | src/backend/tsearch/ts_utils.c | 8 | ||||
-rw-r--r-- | src/backend/tsearch/wparser_def.c | 2 |
4 files changed, 14 insertions, 14 deletions
diff --git a/src/backend/tsearch/ts_locale.c b/src/backend/tsearch/ts_locale.c index 93b550a1a50..75da5068a12 100644 --- a/src/backend/tsearch/ts_locale.c +++ b/src/backend/tsearch/ts_locale.c @@ -90,7 +90,7 @@ t_isprint(const char *ptr) /* - * Set up to read a file using tsearch_readline(). This facility is + * Set up to read a file using tsearch_readline(). This facility is * better than just reading the file directly because it provides error * context pointing to the specific line where a problem is detected. * @@ -168,7 +168,7 @@ tsearch_readline_callback(void *arg) /* * We can't include the text of the config line for errors that occur - * during t_readline() itself. This is only partly a consequence of our + * during t_readline() itself. This is only partly a consequence of our * arms-length use of that routine: the major cause of such errors is * encoding violations, and we daren't try to print error messages * containing badly-encoded data. diff --git a/src/backend/tsearch/ts_typanalyze.c b/src/backend/tsearch/ts_typanalyze.c index 2654d644579..308ae0893c8 100644 --- a/src/backend/tsearch/ts_typanalyze.c +++ b/src/backend/tsearch/ts_typanalyze.c @@ -115,13 +115,13 @@ ts_typanalyze(PG_FUNCTION_ARGS) * language's frequency table, where K is the target number of entries in * the MCELEM array plus an arbitrary constant, meant to reflect the fact * that the most common words in any language would usually be stopwords - * so we will not actually see them in the input. We assume that the + * so we will not actually see them in the input. We assume that the * distribution of word frequencies (including the stopwords) follows Zipf's * law with an exponent of 1. * * Assuming Zipfian distribution, the frequency of the K'th word is equal * to 1/(K * H(W)) where H(n) is 1/2 + 1/3 + ... + 1/n and W is the number of - * words in the language. Putting W as one million, we get roughly 0.07/K. + * words in the language. Putting W as one million, we get roughly 0.07/K. * Assuming top 10 words are stopwords gives s = 0.07/(K + 10). We set * epsilon = s/10, which gives bucket width w = (K + 10)/0.007 and * maximum expected hashtable size of about 1000 * (K + 10). @@ -162,7 +162,7 @@ compute_tsvector_stats(VacAttrStats *stats, TrackItem *item; /* - * We want statistics_target * 10 lexemes in the MCELEM array. This + * We want statistics_target * 10 lexemes in the MCELEM array. This * multiplier is pretty arbitrary, but is meant to reflect the fact that * the number of individual lexeme values tracked in pg_statistic ought to * be more than the number of values for a simple scalar column. @@ -233,7 +233,7 @@ compute_tsvector_stats(VacAttrStats *stats, /* * We loop through the lexemes in the tsvector and add them to our - * tracking hashtable. Note: the hashtable entries will point into + * tracking hashtable. Note: the hashtable entries will point into * the (detoasted) tsvector value, therefore we cannot free that * storage until we're done. */ @@ -300,7 +300,7 @@ compute_tsvector_stats(VacAttrStats *stats, /* * Construct an array of the interesting hashtable items, that is, - * those meeting the cutoff frequency (s - epsilon)*N. Also identify + * those meeting the cutoff frequency (s - epsilon)*N. Also identify * the minimum and maximum frequencies among these items. * * Since epsilon = s/10 and bucket_width = 1/epsilon, the cutoff @@ -333,7 +333,7 @@ compute_tsvector_stats(VacAttrStats *stats, /* * If we obtained more lexemes than we really want, get rid of those - * with least frequencies. The easiest way is to qsort the array into + * with least frequencies. The easiest way is to qsort the array into * descending frequency order and truncate the array. */ if (num_mcelem < track_len) @@ -364,7 +364,7 @@ compute_tsvector_stats(VacAttrStats *stats, * they get sorted on frequencies. The rationale is that we * usually search through most common elements looking for a * specific value, so we can grab its frequency. When values are - * presorted we can employ binary search for that. See + * presorted we can employ binary search for that. See * ts_selfuncs.c for a real usage scenario. */ qsort(sort_table, num_mcelem, sizeof(TrackItem *), diff --git a/src/backend/tsearch/ts_utils.c b/src/backend/tsearch/ts_utils.c index abf53c00197..29cd383b488 100644 --- a/src/backend/tsearch/ts_utils.c +++ b/src/backend/tsearch/ts_utils.c @@ -25,8 +25,8 @@ /* * Given the base name and extension of a tsearch config file, return - * its full path name. The base name is assumed to be user-supplied, - * and is checked to prevent pathname attacks. The extension is assumed + * its full path name. The base name is assumed to be user-supplied, + * and is checked to prevent pathname attacks. The extension is assumed * to be safe. * * The result is a palloc'd string. @@ -39,7 +39,7 @@ get_tsearch_config_filename(const char *basename, char *result; /* - * We limit the basename to contain a-z, 0-9, and underscores. This may + * We limit the basename to contain a-z, 0-9, and underscores. This may * be overly restrictive, but we don't want to allow access to anything * outside the tsearch_data directory, so for instance '/' *must* be * rejected, and on some platforms '\' and ':' are risky as well. Allowing @@ -69,7 +69,7 @@ comparestr(const void *a, const void *b) /* * Reads a stop-word file. Each word is run through 'wordop' - * function, if given. wordop may either modify the input in-place, + * function, if given. wordop may either modify the input in-place, * or palloc a new version. */ void diff --git a/src/backend/tsearch/wparser_def.c b/src/backend/tsearch/wparser_def.c index f66851426b4..b2da46c5872 100644 --- a/src/backend/tsearch/wparser_def.c +++ b/src/backend/tsearch/wparser_def.c @@ -330,7 +330,7 @@ TParserInit(char *str, int len) /* * Use of %.*s here is a bit risky since it can misbehave if the data is - * not in what libc thinks is the prevailing encoding. However, since + * not in what libc thinks is the prevailing encoding. However, since * this is just a debugging aid, we choose to live with that. */ fprintf(stderr, "parsing \"%.*s\"\n", len, str); |