From 84169ce643075f1e49b18744d5609c7f1c48e7f7 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 17 Jun 2020 11:26:11 -0700
Subject: remove unused common.py

---
 python/common.py | 99 --------------------------------------------------------
 1 file changed, 99 deletions(-)
 delete mode 100644 python/common.py

(limited to 'python/common.py')

diff --git a/python/common.py b/python/common.py
deleted file mode 100644
index e596b35..0000000
--- a/python/common.py
+++ /dev/null
@@ -1,99 +0,0 @@
-
-import json
-from datetime import datetime
-
-NORMAL_MIME = (
-    'application/pdf',
-    'application/postscript',
-    'text/html',
-    'text/xml',
-)
-
-def normalize_mime(raw):
-    raw = raw.lower()
-    for norm in NORMAL_MIME:
-        if raw.startswith(norm):
-            return norm
-
-    # Special cases
-    if raw.startswith('application/xml'):
-        return 'text/xml'
-    if raw.startswith('application/x-pdf'):
-        return 'application/pdf'
-    return None
-
-
-def test_normalize_mime():
-    assert normalize_mime("asdf") is None
-    assert normalize_mime("application/pdf") == "application/pdf"
-    assert normalize_mime("application/pdf+journal") == "application/pdf"
-    assert normalize_mime("Application/PDF") == "application/pdf"
-    assert normalize_mime("application/p") is None
-    assert normalize_mime("application/xml+stuff") == "text/xml"
-    assert normalize_mime("application/x-pdf") == "application/pdf"
-    assert normalize_mime("application/x-html") is None
-
-
-def parse_cdx_line(raw_cdx):
-
-    cdx = raw_cdx.split()
-    if len(cdx) < 11:
-        return None
-
-    surt = cdx[0]
-    dt = cdx[1]
-    url = cdx[2]
-    mime = normalize_mime(cdx[3])
-    http_status = cdx[4]
-    key = cdx[5]
-    c_size = cdx[8]
-    offset = cdx[9]
-    warc = cdx[10]
-
-    if not (key.isalnum() and c_size.isdigit() and offset.isdigit()
-            and http_status == "200" and len(key) == 32 and dt.isdigit()
-            and mime != None):
-        return None
-
-    if '-' in (surt, dt, url, mime, http_status, key, c_size, offset, warc):
-        return None
-
-    key = "sha1:{}".format(key)
-
-    info = dict(surt=surt, dt=dt, url=url, c_size=int(c_size),
-        offset=int(offset), warc=warc)
-
-    warc_file = warc.split('/')[-1]
-    try:
-        dt_iso = datetime.strptime(dt, "%Y%m%d%H%M%S").isoformat()
-    except Exception:
-        return None
-
-    # 'i' intentionally not set
-    heritrix = dict(u=url, d=dt_iso, f=warc_file, o=int(offset), c=1)
-    return {'key': key, 'file:mime': mime, 'file:cdx': info, 'f:c': heritrix}
-
-def parse_ungrobided_line(raw_line):
-
-    line = raw_line.strip().split("\t")
-    if len(line) != 4:
-        return None
-
-    key = line[0]
-    mime = normalize_mime(line[2])
-    try:
-        f_c = json.loads(line[1])
-        cdx = json.loads(line[3])
-    except json.JSONDecodeError:
-        return None
-
-    if not (key[5:].isalnum() and len(key) == 37 and mime != None):
-        print(mime)
-        print(key)
-        print("FAIL")
-        return None
-
-    if '-' in (key, mime, f_c, cdx):
-        return None
-
-    return {'key': key, 'file:mime': mime, 'file:cdx': cdx, 'f:c': f_c}
-- 
cgit v1.2.3