From 0ed071c69c2b4f4cdbc0a2aceb4a70b94f54d89a Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Sat, 13 Nov 2021 17:44:20 +0100
Subject: [PATCH] Save output as a FASTA file

---
 data/.gitkeep |  0
 src/parser.py | 21 ++++++++++++++++-----
 2 files changed, 16 insertions(+), 5 deletions(-)
 delete mode 100644 data/.gitkeep

diff --git a/data/.gitkeep b/data/.gitkeep
deleted file mode 100644
index e69de29..0000000
diff --git a/src/parser.py b/src/parser.py
index 3885be3..0c4ec9d 100644
--- a/src/parser.py
+++ b/src/parser.py
@@ -1,8 +1,8 @@
 from argparse import ArgumentParser
 from glob import glob
-from typing import List, Union
+from typing import List
 
-from pandas import DataFrame, read_html
+from pandas import DataFrame, read_html, Series
 
 
 def find_html_files(path) -> List:
@@ -10,17 +10,28 @@ def find_html_files(path) -> List:
     return file_list
 
 
-def extract_adapters(files) -> Union[DataFrame, None]:
+def extract_adapters(files) -> Series:
     all_adapters = DataFrame()
     for entry in files:
         tables = read_html(entry)
         adapter_sequences = tables[1].Sequence
         all_adapters = all_adapters.append(adapter_sequences)
-    return all_adapters.dropna()
+    processed_adapters = preprocess_dataframe(all_adapters)
+    return processed_adapters
+
+
+def preprocess_dataframe(adapters) -> Series:
+    na_free_adapters = adapters.dropna(axis=1)
+    stacked_adapters = na_free_adapters.stack()
+    duplicate_free_adapters = stacked_adapters.drop_duplicates()
+    return duplicate_free_adapters
 
 
 def save_to_file(filename, adapters) -> None:
-    adapters.to_csv(filename, index=False, header=False, sep="\n")
+    with open(filename, "w") as f:
+        for index, value in adapters.iteritems():
+            fasta_entry = f">{index}\n{value}\n"
+            f.write(fasta_entry)
 
 
 def parse_arguments():