revised zipinfo.py nested version

jc/parsers/zipinfo.py

@@ -21,60 +21,56 @@ Usage (module):
 Schema:
 
     {
-      "archive": [
+      "archive":            string,
+      "size":               integer,
+      "size_unit":          string,
+      "number_entries":     integer,
+      "number_files":       integer,
+      "bytes_uncompressed": integer,
+      "bytes_compressed":   integer,
+      "percent_compressed": float,
+      "files": [
         {
-          "name":               string,
+          "flags":      string,
-          "size":               integer,
+          "zipversion": string,
-          "size_unit":          string,
+          "zipunder":   string
-          "number_entries":     integer,
+          "filesize":   integer,
-          "number_files":       integer,
+          "type":       string,
-          "bytes_uncompressed": integer,
+          "method":     string,
-          "bytes_compressed":   integer,
+          "date":       string,
-          "contents": [
+          "time":       string,
-            {
+          "filename":   string
-              "flags":       string,
-              "zipversion":  float,
-              "zipunder":    string
-              "size":        integer,
-              "type":        string,
-              "method":      string,
-              "date":        string,
-              "time":        string,
-              "filename":    string
-            }
-          ] 
         }
-      ]
+      ] 
     }
 
 Examples:
 
     $ zipinfo log4j-core-2.16.0.jar | jc --zipinfo -p
 
-    {
+    [
-      "archive": [
+      {
-        {
+        "archive": "log4j-core-2.16.0.jar",
-          "name": "log4j-core-2.16.0.jar",
+        "size": 1789565,
-          "size": "1789565",
+        "size_unit": "bytes",
-          "size_unit": "bytes,",
+        "number_entries": 1218,
-          "number_entries": "1218",
+        "number_files": 1218,
-          "number_files": "1218",
+        "bytes_uncompressed": 3974141,
-          "bytes_uncompressed": "3974141",
+        "bytes_compressed": 1515455,
-          "bytes_compressed": "1515455",
+        "percent_compressed": 61.9,
-          "contents": [
+        "files": [
-            {
+          {
-              "flags": "-rw-r--r--",
+            "flags": "-rw-r--r--",
-              "zipversion": "2.0",
+            "zipversion": "2.0",
-              "zipunder": "unx",
+            "zipunder": "unx",
-              "size": "19810",
+            "filesize": 19810,
-              "type": "bl",
+            "type": "bl",
-              "method": "defN",
+            "method": "defN",
-              "date": "21-Dec-12",
+            "date": "21-Dec-12",
-              "time": "23:35",
+            "time": "23:35",
-              "filename": "META-INF/MANIFEST.MF"
+            "filename": "META-INF/MANIFEST.MF"
-            },
+          },
     ...
-
 """
 import jc.utils
 import jc.parsers.universal
@@ -108,6 +104,18 @@ def _process(proc_data):
         List of Dictionaries. Structured data to conform to the schema.
     """
 
+    for entry in proc_data:
+        int_list = ['bytes_compressed', 'bytes_uncompressed', 'number_entries', 'number_files', 'size']
+        for key in entry:
+            if key in int_list:
+                entry[key] = jc.utils.convert_to_int(entry[key])
+
+            if key in "files":
+                for d in entry[key]:
+                    for key in d:
+                        if key in "filesize":
+                            d[key] = jc.utils.convert_to_int(d[key])
+
     return proc_data
 
 
@@ -138,38 +146,37 @@ def parse(data, raw=False, quiet=False):
         archive_info = [] 
 
         # 1st line
+        # Archive:  log4j-core-2.16.0.jar
         line = datalist.pop(0)
-        parsed_line = line.split()
+        _, archive = line.split()
-        name = parsed_line[1]
 
         # 2nd line
+        # Zip file size: 1789565 bytes, number of entries: 1218
         line = datalist.pop(0)
-        parsed_line = line.split()
+        _, _, _, size, size_unit, _, _, _, number_entries = line.split()
-        size = parsed_line[3]
+        size_unit = size_unit.rstrip(',')
-        size_unit = parsed_line[4]
-        number_entries = parsed_line[-1]
 
         # last line
+        # 1218 files, 3974141 bytes uncompressed, 1515455 bytes compressed:  61.9%
         line = datalist.pop(-1)
-        parsed_line = line.split()
+        number_files, _, bytes_uncompressed, _, _, bytes_compressed, _, _, percent_compressed = line.split()
-        number_files = parsed_line[0]
+        percent_compressed = float(percent_compressed.rstrip("%"))
-        bytes_uncompressed = parsed_line[2]
-        bytes_compressed = parsed_line[5]
 
         # Add header row for parsing
-        datalist[:0] = ['flags zipversion zipunder size type method date time filename']
+        datalist[:0] = ['flags zipversion zipunder filesize type method date time filename']
 
-        contents_list = jc.parsers.universal.simple_table_parse(datalist)
+        file_list = jc.parsers.universal.simple_table_parse(datalist)
 
-        archive_info.append({'name': name,
+        archive_info.append({'archive': archive,
                              'size': size,
                              'size_unit': size_unit,
                              'number_entries': number_entries,
                              'number_files': number_files,
                              'bytes_uncompressed': bytes_uncompressed,
                              'bytes_compressed': bytes_compressed,
-                             'contents': contents_list})
+                             'percent_compressed': percent_compressed,
+                             'files': file_list})
 
-        raw_output['archive'] = archive_info
+        raw_output = archive_info
 
     return raw_output if raw else _process(raw_output)