Různé úkony s LanGrem a gc.x

/usr/local/langr/rules/bin/gc_ucs2_release.x
Required arguments:
--lex=<path>
Accepted arguments:
--input_file=<path> use given input file instead of stdin, ignored when not '--mode=single'
--mode=(single|filter|batch)	default is 'filter'
--action=(gc|ma|disamb|disheu1|single|gcsingle|connect|listrules|tokenization)			default is 'gc'
--input=(plain|jh_vertical|wide_vertical|tokenized_vertical|jh_csts|wide_csts|tokenized_csts)		default is 'plain'
--output=(native|jh_vertical|wide_vertical|tokenized_vertical|tokenized_vertical_with_tp|jh_csts|wide_csts)		default is 'native'
--trace_deletions=(detailed|stat_used|stat_unused|stat_all|no)		default is 'no'
--morphological_guesser=(yes|no)		default is 'no'
--internal_guesser=(yes|no)		default is 'no'
--print_lemma_variant=(yes|no)		default is 'no'
--print_correct_sentences=(yes|no)		default is 'no'; on gc/gcsingle with native output, print the correct sentences too
--group=<group_name>		unused by default, required with --action=single
--user_abbrevs=<filename>		list of user-defined abbrevs
--empty_positions=(restore|keep|modified)		default is 'keep', applies to any vertical output
--collocations=(restore|keep|modified|modified_subst)	default is 'keep'
--ignore_rules=<filename>	<filename> contains a list of '\n' separated variant identifiers
			These variants will be ignore during the operation. If not set, all rules are active.
--verificator=(yes|no)		default is 'yes'; if set to 'no', correction options are not checked for their correctness
Current settings:
TAG_LENGTH=23

$ extract-stat.pl < /tmp/errlog.log

V aktuálním adresáři vzniknou soubory stat.00001 až stat.nnnnn.

extract-stat.pl

#!/usr/bin/perl
 
my $cnt=0;
my $stat=0;
my $fname="stat";
my $fh;
 
while ($radek = <STDIN>) {
    if ($radek =~ /= STATISTICS/) {
        $cnt++;
        $stat=1;
        $fname="stat." . sprintf("%05d",$cnt);
        print STDERR "$fname\n";
        open($fh,">",$fname);
    } elsif ($radek =~ /= END/) {
        $stat=0;
        close($fh);
    } elsif ($stat eq 1) {
        if ($radek !~ /^Tags/) {
            print $fh $radek;
        }
    }
}

$ /disk3/rules/bin/gc.x --lex=/corp/LEX --action=listrules --group=root0 2> ~/tmp/ROOT0

$ get-stat.sh > STAT

get-stat.sh

#!/bin/bash
 
for w in $(cat ROOT0); do
    let c1=$(fgrep -h -w $w stat.* | cut -f1 | xargs | tr ' ' '+' | bc)
    let c2=$(fgrep -h -w $w stat.* | cut -f2 | xargs | tr ' ' '+' | bc)
    let c3=$(fgrep -h -w $w stat.* | cut -f3 | xargs printf '%.0f\n' | xargs | tr ' ' '+' | bc)
    printf "%9.0f\t%9.0f\t%9.0f\t%s\n" "$c1" "$c2" "$c3" "$w";
done

env BASEDIR=/usr/local/langr/rules USE_MORPHOLOGY=none \
TAGSET_OUR=~skoumal/PROJEKTY/INFRASTRUKTURA/morfologie/MFF-spoluprace/tagset_our.txt.CZ20170531 \
TAGSET_OUR_UNKNOWN=~skoumal/PROJEKTY/INFRASTRUKTURA/morfologie/MFF-spoluprace/tagset_our_unknown.txt.CZ20170531 \
COLLOCATIONS=/usr/local/langr/rules/src/kolokaceGC.win ICONV_IN_CHARSET=CP1250 \
USER_DIR=/usr/local/langr/rules/linguists/hanka/modules/ ./bldlex.sh

env BASEDIR=/usr/local/langr/rules USE_MORPHOLOGY=none \
INTERACTIVE=0 \
TAGSET_OUR=/usr/local/langr/rules/src/ourtags.txt \
TAGSET_OUR_UNKNOWN=/usr/local/langr/rules/src/ourtags_unkn.txt \
COLLOCATIONS=/usr/local/langr/rules/src/kolokaceGC.win \
ICONV_IN_CHARSET=CP1250 \
USER_DIR=/usr/local/langr/rules/linguists/hanka/modules/ \
PROCESS_GROUPS="-i root -i heuristika1" \
CATTRANS=/usr/local/langr/rules/src/cattrans.txt.new \
COMPILER=/usr/local/langr/rules/bin/compiler_ucs2_release.x ./bldlex.sh

parallel-filter.sh -C "${SYN2020_PREFIX}/bin/gc_ucs2_release.x \
--lex=${SYN2020_PREFIX}/LEX_ucs2   --action=single --input=wide_vertical --output=wide_vertical \
--empty_positions=modified --collocations=modified --trace_deletions=stat_all --group=root" \
-s vert-vrbtg8 -t /dev/null -v -p10 2>>errlog/rules_stat.log

extract-stat.pl < errlog/rules_stat.log | sort -k4 | count-stat.pl > rules-stat.log

a setřídit seznam podle počtu použití:

sort -n -k2 rules-stat.log > rules-stat.srt