From 4765005bdb6aaaf5279ddbedf29c520217f3a0ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20Gr=C3=BCning?= Date: Fri, 13 Apr 2018 08:18:45 +0200 Subject: [PATCH 1/2] fix error in ppm calculation --- .../join_files_on_column_fuzzy/join_files_on_column_fuzzy.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.py b/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.py index 1e19f1dcfe..ca326b43d3 100644 --- a/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.py +++ b/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.py @@ -85,7 +85,6 @@ def fill_cache(): fill_cache() elif ppm_dist > args.distance: _cache.append([_c, value2]) - elif ppm_dist < args.distance: fill_cache() if args.closest and write_buffer: write_buffer.sort(key=lambda x: x[0]) From fcf85f78cf68f7bf7905c470d9769d0226b715c0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20Gr=C3=BCning?= Date: Fri, 13 Apr 2018 08:19:09 +0200 Subject: [PATCH 2/2] Update join_files_on_column_fuzzy.xml --- .../join_files_on_column_fuzzy/join_files_on_column_fuzzy.xml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.xml b/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.xml index 6323083959..1560566f8c 100644 --- a/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.xml +++ b/tools/text_processing/join_files_on_column_fuzzy/join_files_on_column_fuzzy.xml @@ -1,4 +1,4 @@ - + on column allowing a small difference