[fauna] Rescue fauna data processing steps

Rescue some of the original functionality of the zika_upload script from fauna.
https://github.com/nextstrain/fauna/blob/master/vdb/zika_upload.py#L14-L30

* Remove monkeypox annotations.tsv
* Move strain name, location, and date fixes to annotations.tsv
* Match strain names in fauna database
* Match locations in fauna database if both region and country names do not match
* Match dates in fauna database unless genbank has been updated

ingest/bin/post_process_metadata.py

@@ -8,6 +8,8 @@
 import pandas as pd
 
 
+import re
+
 def parse_args():
     parser = argparse.ArgumentParser(
         description="Reformat a NCBI Virus metadata.tsv file for a pathogen build."
@@ -27,6 +29,20 @@ def parse_args():
 def _set_strain_name(record):
     """Replace spaces, dashes, and periods with underscores in strain name."""
     strain_name = record["strain"]
+
+    strain_name = strain_name.replace('Zika_virus', '').replace('Zikavirus', '').replace('Zika virus', '').replace('Zika', '').replace('ZIKV', '')
+    strain_name = strain_name.replace('Human', '').replace('human', '').replace('H.sapiens_wt', '').replace('H.sapiens-wt', '').replace('H.sapiens_tc', '').replace('Hsapiens_tc', '').replace('H.sapiens-tc', '').replace('Homo_sapiens', '').replace('Homo sapiens', '').replace('Hsapiens', '').replace('H.sapiens', '')
+    strain_name = strain_name.replace('/Hu/', '')
+    strain_name = strain_name.replace('_Asian', '').replace('_Asia', '').replace('_asian', '').replace('_asia', '')
+    strain_name = strain_name.replace('_URI', '').replace('-URI', '').replace('_SER', '').replace('-SER', '').replace('_PLA', '').replace('-PLA', '').replace('_MOS', '').replace('_SAL', '')
+    strain_name = strain_name.replace('Aaegypti_wt', 'Aedes_aegypti').replace('Aedessp', 'Aedes_sp')
+    strain_name = strain_name.replace(' ', '').replace('\'', '').replace('(', '').replace(')', '').replace('//', '/').replace('__', '_').replace('.', '').replace(',', '')
+    strain_name = re.sub('^[\/\_\-]', '', strain_name)
+
+    try:
+        strain_name = 'V' + str(int(strain_name))
+    except ValueError:
+        pass
 
     return (
         strain_name.replace(" ", "_")