Merge pull request #235 from jawallace/master

Regression Test Refactoring

test/script/Emailer.py

@@ -5,120 +5,45 @@ from email.mime.text import MIMEText
 from email.mime.base import MIMEBase
 from email import encoders
 import xml
-from time import localtime, strftime
 from xml.dom.minidom import parse, parseString
-import subprocess
-import sys
-import os
 
-def send_email(parsed, errorem, attachl, passFail):
-	element = parsed.getElementsByTagName("email")
-	if(len(element)<=0):
-		return
-	element = element[0]
-	toval = element.getAttribute("value").encode().decode("utf_8")
-	if(toval==None):
-		return
-	element = parsed.getElementsByTagName("mail_server")[0]
-	serverval = element.getAttribute("value").encode().decode("utf_8")
-	# Create the container (outer) email message.
-	msg = MIMEMultipart()
-	element = parsed.getElementsByTagName("subject")[0]
-	subval = element.getAttribute("value").encode().decode("utf_8")
-	if(passFail):
-		msg['Subject'] = '[Test]Autopsy ' + subval + ' test passed.'
-	else:
-		msg['Subject'] = '[Test]Autopsy ' + subval + ' test failed.'
-	# me == the sender's email address
-	# family = the list of all recipients' email addresses
-	msg['From'] = 'AutopsyTest'
-	msg['To'] = toval
-	msg.preamble = 'This is a test'
-	container = MIMEText(errorem, 'plain')
-	msg.attach(container)
-	Build_email(msg, attachl)
-	s = smtplib.SMTP(serverval)
-	try:
-		print('Sending Email')
-		s.sendmail(msg['From'], msg['To'], msg.as_string())
-	except Exception as e:
-		print(str(e))
-	s.quit()
+def send_email(to, server, subj, body, attachments):
+    """Send an email with the given information.
 
-def Build_email(msg, attachl):
-	for file in attachl:
-		part = MIMEBase('application', "octet-stream")
-		atach = open(file, "rb")
-		attch = atach.read()
-		noml = file.split("\\")
-		nom = noml[len(noml)-1]
-		part.set_payload(attch)
-		encoders.encode_base64(part)
-		part.add_header('Content-Disposition', 'attachment; filename="' + nom + '"')
-		msg.attach(part)
+    Args:
+        to: a String, the email address to send the email to
+        server: a String, the mail server to send from
+        subj: a String, the subject line of the message
+        body: a String, the body of the message
+        attachments: a listof_pathto_File, the attachements to include
+    """
+    msg = MIMEMultipart()
+    msg['Subject'] = subj
+    # me == the sender's email address
+    # family = the list of all recipients' email addresses
+    msg['From'] = 'AutopsyTest'
+    msg['To'] = to
+    msg.preamble = 'This is a test'
+    container = MIMEText(body, 'plain')
+    msg.attach(container)
+    Build_email(msg, attachments)
+    s = smtplib.SMTP(server)
+    try:
+        print('Sending Email')
+        s.sendmail(msg['From'], msg['To'], msg.as_string())
+    except Exception as e:
+        print(str(e))
+    s.quit()
 
-# Returns a Windows style path starting with the cwd and
-# ending with the list of directories given
-def make_local_path(*dirs):
-	path = wgetcwd().decode("utf-8")
-	for dir in dirs:
-		path += ("\\" + str(dir))
-	return path_fix(path)
+def Build_email(msg, attachments):
+    for file in attachments:
+        part = MIMEBase('application', "octet-stream")
+        atach = open(file, "rb")
+        attch = atach.read()
+        noml = file.split("\\")
+        nom = noml[len(noml)-1]
+        part.set_payload(attch)
+        encoders.encode_base64(part)
+        part.add_header('Content-Disposition', 'attachment; filename="' + nom + '"')
+        msg.attach(part)
 
-# Returns a Windows style path based only off the given directories
-def make_path(*dirs):
-	path = dirs[0]
-	for dir in dirs[1:]:
-		path += ("\\" + str(dir))
-	return path_fix(path)
-	
-# Fix a standard os.path by making it Windows format
-def path_fix(path):
-	return path.replace("/", "\\")
-	
-# Gets the true current working directory instead of Cygwin's
-def wgetcwd():
-	proc = subprocess.Popen(("cygpath", "-m", os.getcwd()), stdout=subprocess.PIPE)
-	out,err = proc.communicate()
-	tst = out.rstrip()
-	if os.getcwd == tst:
-		return os.getcwd
-	else:
-		proc = subprocess.Popen(("cygpath", "-m", os.getcwd()), stdout=subprocess.PIPE)
-		out,err = proc.communicate()
-		return out.rstrip()
-# Verifies a file's existance
-def file_exists(file):
-	try:
-		if os.path.exists(file):
-			return os.path.isfile(file)
-	except:
-		return False
-		
-# Verifies a directory's existance
-def dir_exists(dir):
-	try:
-		return os.path.exists(dir)
-	except:
-		return False
-
-
-
-# Returns the nth word in the given string or "" if n is out of bounds
-# n starts at 0 for the first word
-def get_word_at(string, n):
-	words = string.split(" ")
-	if len(words) >= n:
-		return words[n]
-	else:
-		return ""
-
-# Returns true if the given file is one of the required input files
-# for ingest testing
-def required_input_file(name):
-	if ((name == "notablehashes.txt-md5.idx") or
-	   (name == "notablekeywords.xml") or
-	   (name == "nsrl.txt-md5.idx")): 
-	   return True
-	else:
-		return False

test/script/regression_utils.py

@@ -0,0 +1,154 @@
+import os
+import sys
+import subprocess
+from time import localtime, strftime
+import traceback
+
+# Returns a Windows style path starting with the cwd and
+# ending with the list of directories given
+def make_local_path(*dirs):
+	path = wgetcwd().decode("utf-8")
+	for dir in dirs:
+		path += ("\\" + str(dir))
+	return path_fix(path)
+
+# Returns a Windows style path based only off the given directories
+def make_path(*dirs):
+	path = dirs[0]
+	for dir in dirs[1:]:
+		path += ("\\" + str(dir))
+	return path_fix(path)
+
+# Fix a standard os.path by making it Windows format
+def path_fix(path):
+	return path.replace("/", "\\")
+
+# Gets the true current working directory instead of Cygwin's
+def wgetcwd():
+	proc = subprocess.Popen(("cygpath", "-m", os.getcwd()), stdout=subprocess.PIPE)
+	out,err = proc.communicate()
+	tst = out.rstrip()
+	if os.getcwd == tst:
+		return os.getcwd
+	else:
+		proc = subprocess.Popen(("cygpath", "-m", os.getcwd()), stdout=subprocess.PIPE)
+		out,err = proc.communicate()
+		return out.rstrip()
+# Verifies a file's existance
+def file_exists(file):
+	try:
+		if os.path.exists(file):
+			return os.path.isfile(file)
+	except:
+		return False
+
+# Verifies a directory's existance
+def dir_exists(dir):
+	try:
+		return os.path.exists(dir)
+	except:
+		return False
+
+
+
+# Returns the nth word in the given string or "" if n is out of bounds
+# n starts at 0 for the first word
+def get_word_at(string, n):
+	words = string.split(" ")
+	if len(words) >= n:
+		return words[n]
+	else:
+		return ""
+
+# Returns true if the given file is one of the required input files
+# for ingest testing
+def required_input_file(name):
+	if ((name == "notablehashes.txt-md5.idx") or
+	   (name == "notablekeywords.xml") or
+	   (name == "nsrl.txt-md5.idx")):
+	   return True
+	else:
+		return False
+
+def image_type(image_file):
+    ext_start = image_file.rfind(".")
+    if (ext_start == -1):
+        return IMGTYPE.UNKNOWN
+    ext = image_file[ext_start:].lower()
+    if (ext == ".img" or ext == ".dd"):
+        return IMGTYPE.RAW
+    elif (ext == ".e01"):
+        return IMGTYPE.ENCASE
+    elif (ext == ".aa" or ext == ".001"):
+        return IMGTYPE.SPLIT
+    else:
+        return IMGTYPE.UNKNOWN
+
+# Returns the type of image file, based off extension
+class IMGTYPE:
+    RAW, ENCASE, SPLIT, UNKNOWN = range(4)
+
+def get_image_name(image_file):
+    path_end = image_file.rfind("/")
+    path_end2 = image_file.rfind("\\")
+    ext_start = image_file.rfind(".")
+    if(ext_start == -1):
+        name = image_file
+    if(path_end2 != -1):
+        name = image_file[path_end2+1:ext_start]
+    elif(ext_start == -1):
+        name = image_file[path_end+1:]
+    elif(path_end == -1):
+        name = image_file[:ext_start]
+    elif(path_end!=-1 and ext_start!=-1):
+        name = image_file[path_end+1:ext_start]
+    else:
+        name = image_file[path_end2+1:ext_start]
+    return name
+
+def usage():
+    """Return the usage description of the test script."""
+    return """
+Usage:  ./regression.py [-f FILE] [OPTIONS]
+
+        Run RegressionTest.java, and compare the result with a gold standard.
+        By default, the script tests every image in ../input
+        When the -f flag is set, this script only tests a single given image.
+        When the -l flag is set, the script looks for a configuration file,
+        which may outsource to a new input directory and to individual images.
+
+        Expected files:
+          An NSRL database at:          ../input/nsrl.txt-md5.idx
+          A notable hash database at:    ../input/notablehashes.txt-md5.idx
+          A notable keyword file at:      ../input/notablekeywords.xml
+
+Options:
+  -r            Rebuild the gold standards for the image(s) tested.
+  -i            Ignores the ../input directory and all files within it.
+  -u            Tells Autopsy not to ingest unallocated space.
+  -k            Keeps each image's Solr index instead of deleting it.
+  -v            Verbose mode; prints all errors to the screen.
+  -e ex      Prints out all errors containing ex.
+  -l cfg        Runs from configuration file cfg.
+  -c            Runs in a loop over the configuration file until canceled. Must be used in conjunction with -l
+  -fr           Will not try download gold standard images
+    """
+
+#####
+# Enumeration definition (python 3.2 doesn't have enumerations, this is a common solution
+# that allows you to access a named enum in a Java-like style, i.e. Numbers.ONE)
+#####
+def enum(*seq, **named):
+    enums = dict(zip(seq, range(len(seq))), **named)
+    return type('Enum', (), enums)
+
+
+def get_files_by_ext(dir_path, ext):
+    """Get a list of all the files with a given extenstion in the directory.
+
+    Args:
+        dir: a pathto_Dir, the directory to search.
+        ext: a String, the extension to search for. i.e. ".html"
+    """
+    return [ os.path.join(dir_path, file) for file in os.listdir(dir_path) if
+    file.endswith(ext) ]