tidrange-formats: extends input file with tids

prototype/calculate_tids.py

+"""Extends tidrange-formats.txt with tids
+"""
+
+from __future__ import print_function
+import argparse
+import dateparser
+
+from ZODB.TimeStamp import TimeStamp
+from zodbtools.util import ashex
+
+
+def toTID(dt):
+    return ashex(
+        TimeStamp(
+            dt.year,
+            dt.month,
+            dt.day,
+            dt.hour,
+            dt.minute,
+            dt.second + dt.microsecond / 1000000.0,
+        ).raw()
+    )
+
+
+parser = argparse.ArgumentParser(description="Prototype script for tidrange parsing")
+parser.add_argument(
+    "--formats",
+    default="./zodbtools/test/testdata/tidrange-formats.txt",
+    help="Path of tidrange-formats.txt",
+)
+args = parser.parse_args()
+
+dateparser_settings = {"TO_TIMEZONE": "UTC", "RETURN_AS_TIMEZONE_AWARE": True}
+
+
+with open(args.formats, "r") as f:
+    for line in f:
+        line = line.strip()
+        # skip comments or empty lines
+        if not line or line.startswith("#"):
+            if not (line.startswith("#1") or line.startswith("#2")):
+                print(line)
+                continue
+        reference, timespec = line.split(" ", 1)
+
+        parsed_time = dateparser.parse(
+            reference[1:] if reference.startswith("#") else reference,
+            settings=dateparser_settings,
+        )
+        print(reference, toTID(parsed_time), timespec)

zodbtools/test/testdata/tidrange-formats.txt

@@ -10,82 +10,82 @@
 
 # some absolute date formats:
 # RFC3339
-2018-01-01T10:30:00Z 2018-01-01T10:30:00Z
-1985-04-12T23:20:50Z 1985-04-12T23:20:50.52Z
-1996-12-20T00:39:57Z 1996-12-19T16:39:57-08:00
+2018-01-01T10:30:00Z 03c4857600000000 2018-01-01T10:30:00Z
+1985-04-12T23:20:50Z 02b914f8d5555555 1985-04-12T23:20:50.52Z
+1996-12-20T00:39:57Z 03189927f3333333 1996-12-19T16:39:57-08:00
 
 # RFC822
-1976-08-26T14:29:00Z 26 Aug 76 14:29 GMT
-1976-08-26T12:29:00Z 26 Aug 76 14:29 +02:00
+1976-08-26T14:29:00Z 02728aa500000000 26 Aug 76 14:29 GMT
+1976-08-26T12:29:00Z 02728a2d00000000 26 Aug 76 14:29 +02:00
 
 # RFC850 -> not supported
 # (note that I'm not 100% sure of the expected result here)
-#2006-01-02T22:04:05Z Monday, 02-Jan-06 15:04:05 MST
+#2006-01-02T22:04:05Z 036277cc15555555 Monday, 02-Jan-06 15:04:05 MST
 
 # RFC1123 -> not supported
 # (note that I'm not 100% sure of the expected result here)
-#2006-01-02T22:04:05Z Mon, 02 Jan 2006 15:04:05 MST
+#2006-01-02T22:04:05Z 036277cc15555555 Mon, 02 Jan 2006 15:04:05 MST
 
 # explicit UTC timezone
-2018-01-01T10:30:00Z 2018-01-01 10:30:00 UTC
-2018-01-02T00:00:00Z 2018-01-02 UTC
+2018-01-01T10:30:00Z 03c4857600000000 2018-01-01 10:30:00 UTC
+2018-01-02T00:00:00Z 03c488a000000000 2018-01-02 UTC
 
 
 # Relative formats, based on git's test for approxidate
 # (adapted for timezone Europe/Paris and extended a bit)
-2009-08-30T19:20:00Z now
-2009-08-30T19:19:55Z 5 seconds ago
-2009-08-30T19:19:55Z 5.seconds.ago
-2009-08-30T19:10:00Z 10.minutes.ago
-2009-08-29T19:20:00Z yesterday
-2009-08-27T19:20:00Z 3.days.ago
-2009-08-09T19:20:00Z 3.weeks.ago
-2009-05-30T19:20:00Z 3.months.ago
-2009-08-30T19:19:00Z 1 minute ago
-2009-08-29T19:20:00Z 1 day ago
-2009-07-30T19:20:00Z 1 month ago
+2009-08-30T19:20:00Z 03805ec800000000 now
+2009-08-30T19:19:55Z 03805ec7eaaaaaaa 5 seconds ago
+2009-08-30T19:19:55Z 03805ec7eaaaaaaa 5.seconds.ago
+2009-08-30T19:10:00Z 03805ebe00000000 10.minutes.ago
+2009-08-29T19:20:00Z 0380592800000000 yesterday
+2009-08-27T19:20:00Z 03804de800000000 3.days.ago
+2009-08-09T19:20:00Z 037fe8a800000000 3.weeks.ago
+2009-05-30T19:20:00Z 037e53a800000000 3.months.ago
+2009-08-30T19:19:00Z 03805ec700000000 1 minute ago
+2009-08-29T19:20:00Z 0380592800000000 1 day ago
+2009-07-30T19:20:00Z 037fb06800000000 1 month ago
 
 # go's when does not support "chaining" like this
-#2007-05-30T19:20:00Z 2.years.3.months.ago
+#2007-05-30T19:20:00Z 036dfaa800000000 2.years.3.months.ago
 
-2009-08-29T04:00:00Z 6am yesterday
-2009-08-29T16:00:00Z 6pm yesterday
+2009-08-29T04:00:00Z 0380559000000000 6am yesterday
+2009-08-29T16:00:00Z 0380586000000000 6pm yesterday
 
-2009-08-30T01:00:00Z 3:00
-2009-08-30T13:00:00Z 15:00
-2009-08-30T10:00:00Z noon today
-2009-08-29T10:00:00Z noon yesterday
+2009-08-30T01:00:00Z 03805a7c00000000 3:00
+2009-08-30T13:00:00Z 03805d4c00000000 15:00
+2009-08-30T10:00:00Z 03805c9800000000 noon today
+2009-08-29T10:00:00Z 038056f800000000 noon yesterday
 
 # this input is a bit weird also, what does "noon pm" mean?
 # it seems to trigger a bug in python's parser
 #  TypeError: can't compare offset-naive and offset-aware datetimes
-#2009-01-05T12:00:00Z January 5th noon pm
+#2009-01-05T12:00:00Z 037b0bd000000000 January 5th noon pm
 
 # this input is "ambiguous"
-#2009-08-29T12:00:00Z 10am noon
+#2009-08-29T12:00:00Z 0380577000000000 10am noon
 
 # not supported by date parser
-#2009-08-25T19:20:00Z last tuesday
+#2009-08-25T19:20:00Z 038042a800000000 last tuesday
 # non consistent behavior ( go keep current hour:minutes - python use midnight )
 #  this also TypeError on python
-#2009-07-05T00:00:00Z July 5th
+#2009-07-05T00:00:00Z 037f1f4000000000 July 5th
 
 # parsed as month/day (at least for me ... it might depend on some locale settings other than $TZ ?)
-#2009-05-06T00:00:00Z 06.05.2009
+#2009-05-06T00:00:00Z 037dc82000000000 06.05.2009
 
 # go parser is wrong on this one
-#2009-06-06T05:00:00Z Jun 6, 5AM
+#2009-06-06T05:00:00Z 037e77ac00000000 Jun 6, 5AM
 # go parser is wrong on this one
-#2009-06-06T05:00:00Z 5AM Jun 6
+#2009-06-06T05:00:00Z 037e77ac00000000 5AM Jun 6
 
-2009-06-07T04:00:00Z 6AM, June 7, 2009
+2009-06-07T04:00:00Z 037e7d1000000000 6AM, June 7, 2009
 
 # python and go disagree on these two, go see them as 00:00 UTC
-#2008-11-30T23:00:00Z 2008-12-01
-#2009-11-30T23:00:00Z 2009-12-01
-#2009-06-04T22:00:00Z 06/05/2009
+#2008-11-30T23:00:00Z 037a3e4400000000 2008-12-01
+#2009-11-30T23:00:00Z 03826ac400000000 2009-12-01
+#2009-06-04T22:00:00Z 037e706800000000 06/05/2009
 
 
 ### works with python implementation, but not supported:
-#2018-01-01T09:30:00Z le 1er janvier 2018 à 10h30
-#2018-01-01T23:00:00Z 2018年1月2日
\ No newline at end of file
+#2018-01-01T09:30:00Z 03c4853a00000000 le 1er janvier 2018 à 10h30
+#2018-01-01T23:00:00Z 03c4886400000000 2018年1月2日