cleanup. update expected tar content

.editorconfig

-root = true
-
-[*.java]
-charset = utf-8
-end_of_line = lf
-indent_size = 4
-indent_style = tab
-insert_final_newline = true
-max_line_length = 140
-trim_trailing_whitespace = true
-
-[*.jadd]
-charset = utf-8
-end_of_line = lf
-indent_size = 4
-indent_style = tab
-insert_final_newline = true
-max_line_length = 140
-trim_trailing_whitespace = true
-
-[*.jrag]
-charset = utf-8
-end_of_line = lf
-indent_size = 4
-indent_style = tab
-insert_final_newline = true
-max_line_length = 140
-trim_trailing_whitespace = true

trainbenchmark/results/diff-test.py

-#!/usr/bin/env python
-import csv
-import re
-import os.path
-import sys
-# import subprocess
-import collections
-
-pattern = re.compile('matches-([^-]*)-([^-]*)-railway-([^-]*)-([^-]*)-.csv')
-
-
-class TableRow(object):
-    def __init__(self, size, rowname):
-        self.size = size
-        self.rowname = rowname
-        self.values = {}
-
-    def set(self, index, iteration, value):
-        columns = self.values.get(iteration)
-        if not columns:
-            columns = ['?'] * (self.size)
-            self.values[iteration] = columns
-        columns[index] = value
-
-    def get_rows(self):
-        return [[self.rowname, k] + v + [all((e == v[0] for e in v[1:]))]
-                for k, v in sorted(self.values.iteritems())]
-
-
-class Table(object):
-    def __init__(self):
-        self.rownames = set()
-        self.tools = set()
-        self.rows = collections.OrderedDict()
-
-    def add_tool(self, toolname):
-        self.tools.add(toolname)
-
-    def add_rowname(self, rowname):
-        self.rownames.add(rowname)
-
-    def create_rows(self):
-        def key_rowname(t):
-            tokens = t.rsplit('-', 1)
-            return tokens[0] + tokens[1].zfill(4)
-
-        self.tools = collections.OrderedDict(((e, i) for i, e in enumerate(sorted(self.tools))))
-        self.rownames = sorted(self.rownames, key=key_rowname)
-        for rowname in self.rownames:
-            tr = TableRow(len(self.tools), rowname)
-            self.rows[rowname] = tr
-
-    def set_value(self, rowname, toolname, iteration, value):
-        row = self.rows[rowname]
-        row.set(self.tools[toolname], iteration, value)
-
-    def write(self, fdr):
-        # header
-        writer = csv.writer(fdr)
-        writer.writerow(['Scenario', 'Iteration'] + self.tools.keys() + ['all?'])
-        for _, row in self.rows.iteritems():
-            writer.writerows(row.get_rows())
-
-
-def split_name(filename):
-    """Returns (tool, Query, Scenario, Size)"""
-    m = re.match(pattern, os.path.basename(filename))
-    return m.groups() if m else None
-
-
-def main(directory):
-    table = Table()
-    # first get tool- and row-names
-    for filename in os.listdir(directory):
-        if not filename.startswith('matches'):
-            continue
-        tup = split_name(filename)
-        table.add_tool(tup[0])
-        table.add_rowname('{}-{}-{}'.format(*tup[1:]))
-    table.create_rows()
-    # then fill in the table
-    for filename in os.listdir(directory):
-        if not filename.startswith('matches'):
-            continue
-        with open(os.path.join(directory, filename)) as fdr:
-            reader = csv.reader(fdr)
-            reader.next()  # skip header
-            for row in reader:
-                # Tool, Workload, Description, Model, Run, Query, Iteration, Matches
-                rowname = '{}-{}'.format(row[1], row[3][8:])
-                toolname = row[0]
-                iteration = int(row[6])
-                matches = row[7]
-                table.set_value(rowname, toolname, iteration, matches)
-    with open('summary-{}.csv'.format(os.path.basename(os.path.normpath(directory))), 'w') as fdr:
-        table.write(fdr)
-
-
-if __name__ == '__main__':
-    main(sys.argv[1])

validate_release.sh

-meld <(sort expected_tar_content | sed 's|/$||') <(find ModelValidationWithRAGs/ | sort)
+meld <(expected_tar_content) <(find ModelValidationWithRAGs/)