From: Andrew Lorimer <andrew@charles.cortex>
Date: Tue, 27 Aug 2019 22:05:21 +0000 (+1000)
Subject: add plain text output capability
X-Git-Url: https://git.lorimer.id.au/logparse.git/diff_plain/ccd21602d306c921d1975af58c2339a5f95ff963

add plain text output capability
---

diff --git a/logparse/config.py b/logparse/config.py
index 3e61050..3dc2e46 100644
--- a/logparse/config.py
+++ b/logparse/config.py
@@ -41,7 +41,9 @@ defaults = Configuration({
     'output': '',
     'header':  '/etc/logparse/header.html',
     'css': '/etc/logparse/main.css',
+    'linewidth': 80,
     'embed-styles': False,
+    'plain': False,
     'overwrite': False,
     'title': logparse.__name__,
     'maxlist': 10,
diff --git a/logparse/formatting.py b/logparse/formatting.py
index aa4b71f..d7a9b4d 100644
--- a/logparse/formatting.py
+++ b/logparse/formatting.py
@@ -24,6 +24,250 @@ DEG = u'\N{DEGREE SIGN}'
 CEL = "C"
 TIMEFMT = "%X"
 DATEFMT = "%x"
+CORNERCHARS_DOUBLE = ['╚', '╝', '╗', '╔']
+CORNERCHARS_SINGLE = ['└', '┘', '┐', '┌']
+LINECHARS_DOUBLE = ['║', '═']
+LINECHARS_SINGLE = ['│', '─']
+
+class Output:
+    
+    def __init__(self):
+        self.content = ""
+        self.destination = ""
+
+    def append(self, content):
+        self.content += content
+
+    def write(self, destination=""):
+        if destination == "":
+            destination = self.destination
+        if destination == "":
+            logger.warning("No destination path provided")
+            return 1
+        with open(destination, 'w') as f:
+            f.write(self.content)
+            logger.info("Written output to {}".format(destination))
+
+
+class PlaintextOutput(Output):
+
+    def __init__(self, linewidth=80):
+        self.content = ""
+        self.destination = ""
+        self.linewidth = linewidth;
+
+    def append_header(self, template=''):
+        init_varfilter()
+        box = PlaintextBox(content=Template("$title $version on $hostname\n\n$time $date").safe_substitute(varsubst), vpadding=2, hpadding="\t\t", linewidth=config.prefs['linewidth'])
+        line = PlaintextLine(self.linewidth)
+        self.append(box.draw() + line.draw())
+
+    def append_footer(self):
+        init_varfilter()
+        self.append(PlaintextLine(self.linewidth, vpadding=1).draw())
+        self.append(Template("$hostname $time $date").safe_substitute(varsubst))
+
+    def append_section(self, section):
+        self.append(PlaintextBox(content=section.title, double=False, fullwidth=False, vpadding=0, hpadding=" ").draw())
+        self.append('\n'*2)
+        for data in section.data:
+            self.append(self._fmt_data(data.subtitle, data.items))
+        self.append('\n')
+
+    def _fmt_data(self, subtitle, data = None):   # write title and data
+        if (subtitle == ""):
+            logger.warning("No subtitle provided.. skipping section")
+            return
+
+        if (data == None or len(data) == 0):
+            logger.debug("No data provided.. just printing subtitle")
+            return subtitle + '\n'
+        else:
+            logger.debug("Received data " + str(data))
+            subtitle += ':'
+            if (len(data) == 1):
+                return subtitle + ' ' + data[0] + '\n'
+            else:
+                itemoutput = subtitle + '\n'
+                for datum in data:
+                    datum = '• ' + datum
+                    if len(datum) > config.prefs['linewidth']:
+                        words = datum.split()
+                        if max(map(len, words)) > config.prefs['linewidth']:
+                            raise ValueError("Content width is too small")
+                        res, part, others = [], words[0], words[1:]
+                        for word in others:
+                            if len(' ') + len(word) > config.prefs['linewidth'] - len(part):
+                                res.append(part)
+                                part = word
+                            else:
+                                part += ' ' + word
+                        if part:
+                            res.append(part)
+                        datum = '\n'.join(res)
+                    itemoutput += datum + '\n'
+                return itemoutput
+
+
+class HtmlOutput(Output):
+
+    def __init__(self):
+        self.content = ""
+        self.destination = ""
+        self.css = ""
+
+    def embed_css(self, css):
+        self.content = mail.mailprep(self.content, css)
+
+    def append_header(self, template):   # insert variables into header template file
+        init_varfilter()
+        headercontent = Template(open(template, 'r').read())
+        self.append(headercontent.safe_substitute(varsubst))
+        self.append(opentag('div', id='main'))
+
+    def append_footer(self):
+        self.append(closetag('div') + closetag('body') + closetag('html'))
+
+    def append_section(self, section):
+        self.append(opentag('div', 1, section.title, 'section'))
+        self.append(self._gen_title(section.title))
+        for data in section.data:
+            self.append(self._fmt_data(data.subtitle, data.items))
+        self.append(closetag('div', 1))
+
+    def _gen_title(self, title):  # write title for a section
+        if (title == '' or '\n' in title):
+            logger.error("Invalid title")
+            raise ValueError 
+        logger.debug("Writing title for " + title)
+        return tag('h2', 0, title)
+
+    def _fmt_data(self, subtitle, data = None):   # write title and data
+        if (subtitle == ""):
+            logger.warning("No subtitle provided.. skipping section")
+            return
+
+        if (data == None or len(data) == 0):
+            logger.debug("No data provided.. just printing subtitle")
+            return tag('p', 0, subtitle)
+        else:
+            logger.debug("Received data " + str(data))
+            subtitle += ':'
+            if (len(data) == 1):
+                return tag('p', 0, subtitle + ' ' + data[0])
+            else:
+                output = ""
+                output += tag('p', 0, subtitle)
+                output += opentag('ul', 1)
+                coderegex = re.compile('`(.*)`')
+                for datum in data:
+                    if datum == "" or datum == None:
+                        continue
+                    datum = coderegex.sub(r'<code>{\1}</code>', str(datum))
+                    output += tag('li', 0, datum)
+                output += closetag('ul', 1)
+                return output
+
+
+class Section:
+
+    def __init__(self, title):
+        self.title = title
+        self.data = []
+
+    def add_data(self, data):
+        self.data.append(data)
+
+class Data:
+    
+    def __init__(self, subtitle, items=None):
+        self.subtitle = subtitle
+        self.items = items 
+
+
+class PlaintextLine:
+
+    def __init__(self, linewidth=80, double=True, vpadding=1, hpadding=""):
+        self.linewidth = linewidth
+        self.double = False
+        self.vpadding = vpadding
+        self.hpadding = hpadding
+
+    def draw(self):
+        line = (LINECHARS_DOUBLE[1] if self.double else LINECHARS_SINGLE[1])
+        return "\n" * self.vpadding + self.hpadding +  line * (self.linewidth - 2 * len(self.hpadding)) + self.hpadding + "\n" * self.vpadding
+
+class PlaintextBox:
+
+    def __init__(self, content="", double=True, fullwidth=True, linewidth=80, hpadding="\t", vpadding=1):
+        self.content = content
+        self.fullwidth = fullwidth
+        self.linewidth = linewidth
+        self.hpadding = hpadding 
+        self.vpadding = vpadding
+        self.double = double
+
+    def draw(self):
+
+        if self.double == True:
+            cornerchars = CORNERCHARS_DOUBLE
+            linechars = LINECHARS_DOUBLE
+        else:
+            cornerchars = CORNERCHARS_SINGLE
+            linechars = LINECHARS_SINGLE
+
+        # Check hpadding has a definite width
+        self.hpadding = self.hpadding.replace("\t", " "*4)
+
+        # Calculate number of characters per line
+        contentlines = self.content.splitlines()
+        contentwidth = int((self.linewidth if self.linewidth > 0 else 80) if self.content.splitlines() else len(max(contentlines, key=len)))
+        logger.debug("Contentwidth is {0}".format(str(contentwidth)))
+        logger.debug("Longest line is {0}".format(len(max(contentlines, key=len))))
+        contentwidth += -2*(len(self.hpadding)+1)
+        if not self.fullwidth:
+            longestline = len(max(contentlines, key=len))
+            if longestline <= self.linewidth - 2*(len(self.hpadding)+1):
+                contentwidth = longestline
+
+        # Split lines that are too long
+        for i, line in enumerate(contentlines):
+            if len(line) > contentwidth:
+                words = line.split()
+                if max(map(len, words)) > contentwidth:
+                    raise ValueError("Content width is too small")
+                res, part, others = [], words[0], words[1:]
+                for word in others:
+                    if len(' ') + len(word) > contentwidth - len(part):
+                        res.append(part)
+                        part = word
+                    else:
+                        part += ' ' + word
+                if part:
+                    res.append(part)
+                contentlines[i] = res
+
+        # Flatten list
+        #   Note list comprehension doesn't work here, so we must iterate through each item
+        newlines = []
+        for line in contentlines:
+            if isinstance(line, list):
+                for subline in line:
+                    newlines.append(subline)
+            else:
+                newlines.append(line)
+        contentlines = newlines
+               
+        # Add vertical padding
+        for _ in range(self.vpadding):
+            contentlines.insert(0, ' '*contentwidth)
+            contentlines.append(' '*contentwidth)
+
+        # Insert horizontal padding on lines that are too short
+        contentlines = [linechars[0] + self.hpadding + x + ' '*(self.linewidth-(len(x)+2*len(self.hpadding)+2) if len(x) < contentwidth else 0) + self.hpadding + linechars[0] for x in contentlines]
+        contentlines.insert(0, cornerchars[3] + linechars[1] * (contentwidth + len(self.hpadding)*2) + cornerchars[2])
+        contentlines.append(cornerchars[0] + linechars[1] * (contentwidth + len(self.hpadding)*2) + cornerchars[1])
+        return ('\n').join(contentlines)
 
 def init_varfilter():
     global varfilter
@@ -66,16 +310,6 @@ def tag(tag, block = 0, content = ""):  # write html opening tag, content, and h
     c = closetag(tag, block)
     return o + content + c
 
-def header(template):   # return a parsed html header from file
-#    try:
-#        copyfile(config['css'], config['dest'] + '/' + os.path.basename(config['css']))
-#        logger.debug("copied main.css")
-#    except Exception as e:
-#        logger.warning("could not copy main.css - " + str(e))
-    init_varfilter()
-    headercontent = Template(open(template, 'r').read())
-    return headercontent.safe_substitute(varsubst)
-
 def orderbyfreq(l):     # order a list by the frequency of its elements and remove duplicates
     temp_l = l[:]
     l = list(set(l))
diff --git a/logparse/interface.py b/logparse/interface.py
index f9a76b2..a9bd2e1 100644
--- a/logparse/interface.py
+++ b/logparse/interface.py
@@ -46,6 +46,7 @@ def main():
     argparser.add_argument('-l', '--logs', help='services to analyse', required=False)
     argparser.add_argument('-nl', '--ignore-logs', help='skip these services (takes precedence over -l)', required=False)
     argparser.add_argument('-es', '--embed-styles', help='make CSS rules inline rather than linking the file', required=False, default=False, action='store_true')
+    argparser.add_argument('-nh', '--plain', help='write/send plain text rather than HTML', required = False, default=False, action='store_true')
 
     # Load config
     if argparser.parse_args().config:
@@ -74,11 +75,15 @@ def main():
     logger.info("Beginning log analysis at {0} {1}".format(start.strftime(formatting.DATEFMT), start.strftime(formatting.TIMEFMT)))
     logger.debug("This is {0} version {1}, running on Python {2}".format(logparse.__name__, logparse.__version__, sys.version.replace('\n', '')))
      
-    # Write HTML header
+    # Write header
 
-    global output_html
-    output_html = formatting.header(prefs['header'])
-    output_html += formatting.opentag('div', id='main')
+    global output
+    if argparser.parse_args().plain:
+        output = formatting.PlaintextOutput(linewidth=prefs['linewidth'])
+    else:
+        output = formatting.HtmlOutput()
+
+    output.append_header(prefs['header'])
 
     # Find parsers
     
@@ -117,32 +122,27 @@ def main():
 
     logger.debug(str(parser_providers))
     for parser in parser_providers:
-        output_html += parser.parse_log()
+        output.append_section(parser.parse_log())
 
     # Write HTML footer
-
-    output_html += formatting.closetag('div') + formatting.closetag('body') + formatting.closetag('html')
+    output.append_footer()
 
     if argparser.parse_args().printout:
-        print(output_html)
+        print(output)
     if argparser.parse_args().destination or prefs['output']:
         if argparser.parse_args().destination:
             dest_path = argparser.parse_args().destination
         else:
             dest_path = prefs['output']
         logger.debug("Outputting to {0}".format(dest_path))
-        if argparser.parse_args().embed_styles or prefs['embed-styles']:
-            output_html = mail.mailprep(output_html, prefs['css'])
-        if not os.path.isfile(dest_path) and not (argparser.parse_args().overwrite or config['overwrite']):
-            with open(dest_path, 'w') as f:
-                f.write(output_html)
-                logger.info("Written output to {}".format(dest_path))
+        if (argparser.parse_args().embed_styles or prefs['embed-styles']) and not (argparser.parse_args.plain or prefs['plain']):
+            output.embed_css(prefs['css'])
+        if (not os.path.isfile(dest_path)) and not (argparser.parse_args().overwrite or config['overwrite']):
+            output.write(dest_path)
         else:
             logger.warning("Destination file already exists")
             if input("Would you like to overwrite {0}? (y/n) [n] ".format(dest_path)) == 'y':
-                with open(dest_path, 'w') as f:
-                    f.write(output_html)
-                logger.debug("Written output to {}".format(dest_path))
+                output.write(dest_path)
             else:
                 logger.warning("No output written")
 
@@ -151,7 +151,8 @@ def main():
             to = argparser.parse_args().to
         else:
             to = prefs['mail']['to']
-        mail.sendmail(mailbin=prefs['mail']['mailbin'], body=mail.mailprep(output_html, prefs['css']), recipient=to, subject=formatting.fsubject(config.prefs['mail']['subject']))
+        if argparser.parse_args().plain or prefs['plain']:
+            mail.sendmail(mailbin=prefs['mail']['mailbin'], body=(output.embed_css(prefs['css']) if isinstance(output, formatting.HtmlOutput) else output.content), recipient=to, subject=formatting.fsubject(config.prefs['mail']['subject']))
     
     # Print end message
     finish = datetime.now()
diff --git a/logparse/parsers/cron.py b/logparse/parsers/cron.py
index 2c7289b..3aba140 100644
--- a/logparse/parsers/cron.py
+++ b/logparse/parsers/cron.py
@@ -14,9 +14,8 @@ import logging
 logger = logging.getLogger(__name__)
 
 def parse_log():
-    output = ''
     logger.debug("Starting cron section")
-    output += opentag('div', 1, 'cron', 'section')
+    section = Section("cron")
     matches = re.findall('.*CMD\s*\(\s*(?!.*cd)(.*)\)', readlog(config.prefs['logs']['cron']))
     num = sum(1 for line in matches)
     commands = []
@@ -26,13 +25,11 @@ def parse_log():
     #logger.debug("found cron command " + str(commands))
     logger.info("Found " + str(num) + " cron jobs")
     subtitle = str(num) + " cron jobs run"
-    output += writetitle("cron")
-    output += writedata(subtitle)
+    section.add_data(Data(subtitle))
     if (len(matches) > 0):
-        commands = addtag(commands, 'code')
-        commands = orderbyfreq(commands)
+        commands = ("`{0}`".format(x) for x in commands)
+        commands = orderbyfreq(list(commands))
         commands = truncl(commands, config.prefs['maxcmd'])
-        output += writedata("top cron commands", [c for c in commands])
-    output += closetag('div', 1)
+        section.add_data(Data("top cron commands", commands))
     logger.info("Finished cron section")
-    return output
+    return section