From 9f159df451bdec96c2a2a99349999d72b4733f17 Mon Sep 17 00:00:00 2001
From: David Lougheed <david.lougheed@gmail.com>
Date: Fri, 17 Nov 2023 10:27:56 -0500
Subject: [PATCH] docs: update README with GA4GH hash

---
 README.md | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/README.md b/README.md
index 2a264a0..ba307cf 100644
--- a/README.md
+++ b/README.md
@@ -23,17 +23,17 @@ fasta-checksum-utils ./my-fasta.fa[.gz]
 This will print output in the following tab-delimited format:
 
 ```
-file  [file size in bytes]    MD5 [file MD5 hash]           TRUNC512  [file TRUNC512 hash]
-chr1  [chr1 sequence length]  MD5 [chr1 sequence MD5 hash]  TRUNC512  [chr1 sequence TRUNC512 hash]
-chr2  [chr2 sequence length]  MD5 [chr2 sequence MD5 hash]  TRUNC512  [chr2 sequence TRUNC512 hash]
+file  [file size in bytes]    md5 [file MD5 hash]           ga4gh  [file GA4GH hash]
+chr1  [chr1 sequence length]  md5 [chr1 sequence MD5 hash]  ga4gh  [chr1 sequence GA4GH hash]
+chr2  [chr2 sequence length]  md5 [chr2 sequence MD5 hash]  ga4gh  [chr2 sequence GA4GH hash]
 ...
 ```
 
 The following example is the output generated by specifying the SARS-CoV-2 genome FASTA from NCBI:
 
 ```
-file        30429  MD5  863ee5dba1da0ca3f87783782284d489  TRUNC512  3036e94352072c8cd4b5d2e855a72af3d4ca010f6fac1353
-NC_045512.2 29903  MD5  105c82802b67521950854a851fc6eefd  TRUNC512  4b2195260fd845e771bec8e9a8d754832caac7b9547eefc3
+file	    30428	md5	825ab3c54b7a67ff2db55262eb532438	ga4gh	SQ.mMg8qNej7pU84juQQWobw9JyUy09oYdd
+NC_045512.2	29903	md5	105c82802b67521950854a851fc6eefd	ga4gh	SQ.SyGVJg_YRedxvsjpqNdUgyyqx7lUfu_D
 ```
 
 If the `--out-format bento-json` arguments are passed, the tool will instead output the report in a JSON
@@ -43,20 +43,24 @@ is the output generated by specifying the SARS-CoV-2 genome:
 
 ```json
 {
-  "md5": "863ee5dba1da0ca3f87783782284d489",
-  "trunc512": "3036e94352072c8cd4b5d2e855a72af3d4ca010f6fac1353",
-  "fasta_size": 30429,
+  "fasta": "sars_cov_2.fa",
+  "fasta_size": 30428,
+  "md5": "825ab3c54b7a67ff2db55262eb532438",
+  "ga4gh": "SQ.mMg8qNej7pU84juQQWobw9JyUy09oYdd",
   "contigs": [
     {
       "name": "NC_045512.2",
       "md5": "105c82802b67521950854a851fc6eefd",
-      "trunc512": "4b2195260fd845e771bec8e9a8d754832caac7b9547eefc3",
+      "ga4gh": "SQ.SyGVJg_YRedxvsjpqNdUgyyqx7lUfu_D",
       "length": 29903
     }
   ]
 }
 ```
 
+If an argument like `--fai [path or URL]` is passed, an additional `"fai": "..."` property will be added to the JSON 
+object output.
+
 If an argument like `--genome-id GRCh38` is provided, an additional `"id": "GRCh38"` property will be added to the
 JSON object output.
 
@@ -80,12 +84,12 @@ async def demo():
     print(file_checksum)
     # prints "863ee5dba1da0ca3f87783782284d489"
     
-    all_algorithms = (fc.algorithms.AlgorithmMD5, fc.algorithms.AlgorithmTRUNC512)
+    all_algorithms = (fc.algorithms.AlgorithmMD5, fc.algorithms.AlgorithmGA4GH)
     
     # calculate multiple checksums for a whole file
     all_checksums: tuple[str, ...] = await fc.checksum_file(file=covid_genome, algorithms=all_algorithms)
     print(all_checksums)
-    # prints tuple: ("863ee5dba1da0ca3f87783782284d489", "3036e94352072c8cd4b5d2e855a72af3d4ca010f6fac1353")
+    # prints tuple: ("863ee5dba1da0ca3f87783782284d489", "SQ.mMg8qNej7pU84juQQWobw9JyUy09oYdd")
     
     # calculate an MD5 and TRUNC512 checksum for a specific contig in a PySAM FASTA file:
     fh = pysam.FastaFile(str(covid_genome))
@@ -96,7 +100,7 @@ async def demo():
             algorithms=all_algorithms,
         )
         print(contig_checksums)
-        # prints tuple: ("105c82802b67521950854a851fc6eefd", "4b2195260fd845e771bec8e9a8d754832caac7b9547eefc3")
+        # prints tuple: ("105c82802b67521950854a851fc6eefd", "SQ.SyGVJg_YRedxvsjpqNdUgyyqx7lUfu_D")
     finally:
         fh.close()  # always close the file handle