From fb3616e06ca20ffe78dfb00b962a2599a46b2a5f Mon Sep 17 00:00:00 2001 From: Dirk Engling Date: Sat, 29 Jun 2019 18:51:00 +0200 Subject: Clean up 1992 post processing --- src/postprocess/postprocess-1992.sh | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'src/postprocess/postprocess-1992.sh') diff --git a/src/postprocess/postprocess-1992.sh b/src/postprocess/postprocess-1992.sh index 1e685d2..6720991 100644 --- a/src/postprocess/postprocess-1992.sh +++ b/src/postprocess/postprocess-1992.sh @@ -4,19 +4,16 @@ paste 1992_Q2/{01_Flags,12_Vorwahl,12_Vorwahl_block,11_Ort,07_Strasse,08_Hausnum # Generate lookup file from 1995 paste 1995_Q0/{12_Vorwahl,11_Ort,07_Strasse,08_Hausnummer,02_Nachname,03_Vorname,13_Rufnummer,10_Postleitzahl} | tr '\n\t' '\0' > 1995-voshnvrp.bin -# To debug in lldb -process launch -i 1992_testfile.txt -- 1995-vorwahl-ort-strasse-hnr-name-vorname-rufnummer-plz.bin - # Compile plz mapper cc -O3 -o map_plz map_plz.c -I ../src/export/ ../src/export/mystdlib.c +# To debug in lldb +# cc -O0 -g -o map_plz map_plz.c -I ../src/export/ ../src/export/mystdlib.c +# process launch -i 1992_testfile.txt -- 1995-vorwahl-ort-strasse-hnr-name-vorname-rufnummer-plz.bin + # outputs mapped plz, generates brutemap.txt touch brutemap_input.bin zip_simple_map.bin -./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 10_Postleitzahl - -# generate street name translation table from brutemap, -# only taking into account similar street names -# cut -f 3,4 brutemap.txt | tr '[:upper:]' '[:lower:]' | paste brutemap.txt - | cut -f 1-4,6,7 | ./jaro | cut -f 1-5 > brutemap_filtered.txt +./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 1992_Q2/10_Postleitzahl # generate street name translation table from brutemap, # only taking into account similar street names, new style @@ -29,4 +26,4 @@ cut -f 1-5 brutemap_simifiltered.txt | sort | uniq -c | sed -E $'s:^ *([[:digit: sort -u zip_mapfile.txt | tr '\n' '\0' > zip_simple_map.bin # Redo the mapping with the data from brutemap and zipmap -./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 10_Postleitzahl +./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 1992_Q2/10_Postleitzahl -- cgit v1.2.3