test: Make changes to reflect minor differences in behavior

nextstrain · Jul 30, 2022 · 0385409 · 0385409
1 parent a928406
commit 0385409
Show file tree

Hide file tree

Showing 5 changed files with 14 additions and 5 deletions.
diff --git a/tests/functional/filter/cram/filter-metadata-sequence-strains-mismatch.t b/tests/functional/filter/cram/filter-metadata-sequence-strains-mismatch.t
@@ -34,6 +34,10 @@ Pandas engine
 SQLite engine
 -------------
 
+The output is slightly different because the SQLite engine only reports one row
+per strain, in contrast to the pandas engine which reports the same strain
+being both excluded then re-included.
+
   $ ${AUGUR} filter --engine sqlite \
   >  --sequence-index filter/data/sequence_index.tsv \
   >  --metadata filter/data/metadata.tsv \
@@ -45,10 +49,10 @@ SQLite engine
   >  --output-log "$TMP/filtered_log.tsv"
   4 strains were dropped during filtering
   \t1 had no metadata (esc)
+  \t2 of these were filtered out by the query: "country != 'Colombia'" (esc)
   \t1 had no sequence data (esc)
-  \t3 of these were filtered out by the query: "country != 'Colombia'" (esc)
   \t1 strains were added back because they were in filter/data/include.txt (esc)
   9 strains passed all filters
 
-  $ diff -u <(sort -k 1,1 filter/data/filtered_log.tsv) <(sort -k 1,1 "$TMP/filtered_log.tsv")
+  $ diff -u <(sort -k 1,1 filter/data/filtered_log_sqlite_engine.tsv) <(sort -k 1,1 "$TMP/filtered_log.tsv")
   $ rm -f "$TMP/filtered_strains.txt"
diff --git a/tests/functional/filter/cram/filter-min-max-date-output.t b/tests/functional/filter/cram/filter-min-max-date-output.t
@@ -27,6 +27,6 @@ SQLite engine
   >  --max-date 2016-02-01 \
   >  --output-metadata "$TMP/filtered_metadata.tsv"
   8 strains were dropped during filtering
-  \t1 of these were dropped because they were earlier than 2015.0 or missing a date (esc)
   \t7 of these were dropped because they were later than 2016.09 or missing a date (esc)
+  \t1 of these were dropped because they were earlier than 2015.0 or missing a date (esc)
   4 strains passed all filters
diff --git a/tests/functional/filter/cram/subsample-probabilistic-sampling-not-always-used.t b/tests/functional/filter/cram/subsample-probabilistic-sampling-not-always-used.t
@@ -34,7 +34,7 @@ SQLite engine
   >  --output-metadata "$TMP/filtered_metadata.tsv"
   Sampling at 10 per group.
   2 strains were dropped during filtering
-  \t1 were dropped during grouping due to ambiguous year information (esc)
   \t1 were dropped during grouping due to ambiguous month information (esc)
+  \t1 were dropped during grouping due to ambiguous year information (esc)
   \t0 of these were dropped because of subsampling criteria, using seed 314159 (esc)
   10 strains passed all filters
diff --git a/tests/functional/filter/cram/subsample-probabilistic-sampling-output.t b/tests/functional/filter/cram/subsample-probabilistic-sampling-output.t
@@ -36,7 +36,7 @@ SQLite engine
   WARNING: Asked to provide at most 3 sequences, but there are 8 groups.
   Sampling probabilistically at 0.3633 sequences per group, meaning it is possible to have more than the requested maximum of 3 sequences after filtering.
   10 strains were dropped during filtering
-  \t1 were dropped during grouping due to ambiguous year information (esc)
   \t1 were dropped during grouping due to ambiguous month information (esc)
+  \t1 were dropped during grouping due to ambiguous year information (esc)
   \t8 of these were dropped because of subsampling criteria, using seed 314159 (esc)
   2 strains passed all filters
diff --git a/tests/functional/filter/data/filtered_log_sqlite_engine.tsv b/tests/functional/filter/data/filtered_log_sqlite_engine.tsv
@@ -0,0 +1,5 @@
+strain	filter	kwargs
+HND/2016/HU_ME59	filter_by_sequence_index	[]
+Colombia/2016/ZC204Se	filter_by_query	"[[""query"", ""country != 'Colombia'""]]"
+COL/FLR_00024/2015	filter_by_query	"[[""query"", ""country != 'Colombia'""]]"
+COL/FLR_00008/2015	force_include_strains	"[[""include_file"", ""filter/data/include.txt""]]"