update size estimate accuracy when seperator option applied

Author: tp7309

.gitignore

@@ -2,7 +2,7 @@
 out.dict
 out.dict.1
 out.dict.2
-README.rst
+coverage_html/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

README.md

@@ -96,8 +96,8 @@ generated password displayed line by line in `OUTPUT`. It is recommended to use
 
 **[]{m:n:r}**
 ```
-when repeatMode is `?`, [123]{1,2} -> 1 2 3 12 13 21 23 31 32
-when repeatMode is `*`, [123]{1,2} -> 1 2 3 11 12 13 21 22 23 31 32 33
+when repeatMode is `?`, [123]{1,2:?} -> 1 2 3 12 13 21 23 31 32
+when repeatMode is `*`, [123]{1,2:*} -> 1 2 3 11 12 13 21 22 23 31 32 33
 ```
 
 **[]{m:n}**

README.rst

@@ -132,8 +132,8 @@ Repeat mode
 
 ::
 
-    when repeatMode is `?`, [123]{1,2} -> 1 2 3 12 13 21 23 31 32
-    when repeatMode is `*`, [123]{1,2} -> 1 2 3 11 12 13 21 22 23 31 32 33
+    when repeatMode is `?`, [123]{1,2:?} -> 1 2 3 12 13 21 23 31 32
+    when repeatMode is `*`, [123]{1,2:*} -> 1 2 3 11 12 13 21 22 23 31 32 33
 
 **[]{minLength:maxLength}** default use ``global_repeat_mode`` option.
 

README_zh_CN.md

@@ -90,8 +90,8 @@ Options:
 
 **[]{m:n:r}**  重复m次到n次，重复模式(r)支持`?`或`*`。
 ```
-repeatMode为 `?`, [123]{1,2} -> 1 2 3 12 13 21 23 31 32
-repeatMode为 `*`, [123]{1,2} -> 1 2 3 11 12 13 21 22 23 31 32 33
+repeatMode为 `?`, [123]{1,2:?} -> 1 2 3 12 13 21 23 31 32
+repeatMode为 `*`, [123]{1,2:*} -> 1 2 3 11 12 13 21 22 23 31 32 33
 ```
 
 **[]{m:n}** 重复m次到n次，重复模式未定义时采用`global_repeat_mode`选项定义的值。

tests/test_TTPassGen.py

@@ -101,6 +101,7 @@ def test_dict_mark_charset_rule(self):
 
     def test_word_seperator(self):
         self.assertEquals(go('$0[abc]?', seperator=' '), 1)
+        self.assertEquals(go('$0[abc]?', seperator='-------------------------\n'), 24)
 
 
     def test_multi_dict_mark_charset_rule(self):

ttpassgen/ttpassgen.py

@@ -97,7 +97,7 @@ class DictRule(object):
     def __init__(self, order, dictPath):
         self.order = order;
         self.dictPath = dictPath;
-
+#Rule class end
 
 class WordProductor(object):
     def __init__(self, countList, sizeList, productors):
@@ -114,14 +114,13 @@ def prod(cls, iterable):
     def totalCount(self):
         return self.prod(self.countList)
 
-    def totalSize(self):
+    def totalSize(self, sep=os.linesep):
         total = 0
         tCount = self.totalCount()
         for i, size in enumerate(self.sizeList):
             total += size * tCount / self.countList[i]
-        total += tCount * len(os.linesep)
+        total += tCount * len(sep)
         return total
-#Rule class end
 
 
 def prettySize(size_bytes):
@@ -164,16 +163,19 @@ def getCharsetRuleResultDataSize(rule):
             size += count * wordLength
     return count, size
 
+
 def getDictRuleResultDataSize(rule):
     sumLines = 0
+    sepLen = 1
     with open(rule.dictPath, 'r') as f:
         bufferSize = 1024 * 4
         readFunc = f.read #loop optimization
         chunk = readFunc(bufferSize)
+        if '\r\n' in chunk: sepLen = 2
         while chunk:
             sumLines += chunk.count('\n')
             chunk = readFunc(bufferSize)
-    linSeperatorCount = len(os.linesep) * sumLines
+    linSeperatorCount = sepLen * sumLines
     return sumLines, (os.path.getsize(rule.dictPath) - linSeperatorCount)
 
 
@@ -334,7 +336,7 @@ def productCombinationWords(result, rules, dictCacheLimit, partSize, appendMode,
     productor = generateWordProductor(rules, dictCacheLimit)
     result[1] = int(productor.totalCount())
     result[0] = 1
-    estimatedSize = prettySize(productor.totalSize())
+    estimatedSize = prettySize(productor.totalSize(sep=seperator))
     print(("estimated size: %s, generate dict...")%(estimatedSize))
 
     if not os.path.exists(os.path.abspath(os.path.join(output, os.path.pardir))):
@@ -477,4 +479,4 @@ def cli(mode, dictlist, rule, dict_cache, global_repeat_mode, part_size, append_
 
 if __name__ == "__main__":
     cli()
-    # cli.main(['-d', 'tests/in.dict', '-r', '[?l]{5}', out.dict'])
+    # cli.main(['-d', '../tests/in.dict', '-r', '[?l]{5}', 'out.dict'])