diff options
author | Dirk Engling <erdgeist@erdgeist.org> | 2019-06-29 18:51:00 +0200 |
---|---|---|
committer | Dirk Engling <erdgeist@erdgeist.org> | 2019-06-29 18:51:00 +0200 |
commit | fb3616e06ca20ffe78dfb00b962a2599a46b2a5f (patch) | |
tree | fe7ad54e8cb17174b3296b63f41ad1f5b1038f8e /src/postprocess/postprocess-1992.sh | |
parent | b4bf8417af0d8ebff2c50570c70fdecaf6a53ed9 (diff) |
Clean up 1992 post processing
Diffstat (limited to 'src/postprocess/postprocess-1992.sh')
-rw-r--r-- | src/postprocess/postprocess-1992.sh | 15 |
1 files changed, 6 insertions, 9 deletions
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 | |||
4 | # Generate lookup file from 1995 | 4 | # Generate lookup file from 1995 |
5 | 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 | 5 | 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 |
6 | 6 | ||
7 | # To debug in lldb | ||
8 | process launch -i 1992_testfile.txt -- 1995-vorwahl-ort-strasse-hnr-name-vorname-rufnummer-plz.bin | ||
9 | |||
10 | # Compile plz mapper | 7 | # Compile plz mapper |
11 | cc -O3 -o map_plz map_plz.c -I ../src/export/ ../src/export/mystdlib.c | 8 | cc -O3 -o map_plz map_plz.c -I ../src/export/ ../src/export/mystdlib.c |
12 | 9 | ||
10 | # To debug in lldb | ||
11 | # cc -O0 -g -o map_plz map_plz.c -I ../src/export/ ../src/export/mystdlib.c | ||
12 | # process launch -i 1992_testfile.txt -- 1995-vorwahl-ort-strasse-hnr-name-vorname-rufnummer-plz.bin | ||
13 | |||
13 | # outputs mapped plz, generates brutemap.txt | 14 | # outputs mapped plz, generates brutemap.txt |
14 | touch brutemap_input.bin zip_simple_map.bin | 15 | touch brutemap_input.bin zip_simple_map.bin |
15 | ./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 10_Postleitzahl | 16 | ./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 1992_Q2/10_Postleitzahl |
16 | |||
17 | # generate street name translation table from brutemap, | ||
18 | # only taking into account similar street names | ||
19 | # 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 | ||
20 | 17 | ||
21 | # generate street name translation table from brutemap, | 18 | # generate street name translation table from brutemap, |
22 | # only taking into account similar street names, new style | 19 | # 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: | |||
29 | sort -u zip_mapfile.txt | tr '\n' '\0' > zip_simple_map.bin | 26 | sort -u zip_mapfile.txt | tr '\n' '\0' > zip_simple_map.bin |
30 | 27 | ||
31 | # Redo the mapping with the data from brutemap and zipmap | 28 | # Redo the mapping with the data from brutemap and zipmap |
32 | ./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 10_Postleitzahl | 29 | ./map_plz 1995-voshnvrp.bin zip_simple_map.bin brutemap_input.bin < 1992-fvvoshnvrpp.txt > 1992_Q2/10_Postleitzahl |