From 349d758c1485661852446e67d9637e1772a72207 Mon Sep 17 00:00:00 2001
From: Michael Hohn <hohn@github.com>
Date: Fri, 2 Aug 2024 13:56:47 -0700
Subject: [PATCH] Move session scripts to separate directory

---
 .../db-generate-selection.py}                 |  0
 .../db-initial-info.py}                       |  0
 .../db-populate-minio.py}                     |  0
 .../db-post-refine-info.py}                   |  1 +
 .../session2.py => session/db-refine-info.py} |  2 +-
 .../db-unique-1.py}                           |  0
 client/qldbtools/session/db-unique.py         | 46 +++++++++++++++++++
 7 files changed, 48 insertions(+), 1 deletion(-)
 rename client/qldbtools/{qldbtools/session-generate-selection.py => session/db-generate-selection.py} (100%)
 rename client/qldbtools/{qldbtools/session1.py => session/db-initial-info.py} (100%)
 rename client/qldbtools/{qldbtools/session-populate-minio.py => session/db-populate-minio.py} (100%)
 rename client/qldbtools/{qldbtools/session-post-refine-info.py => session/db-post-refine-info.py} (97%)
 rename client/qldbtools/{qldbtools/session2.py => session/db-refine-info.py} (98%)
 rename client/qldbtools/{qldbtools/session-4-unique.py => session/db-unique-1.py} (100%)
 create mode 100644 client/qldbtools/session/db-unique.py

diff --git a/client/qldbtools/qldbtools/session-generate-selection.py b/client/qldbtools/session/db-generate-selection.py
similarity index 100%
rename from client/qldbtools/qldbtools/session-generate-selection.py
rename to client/qldbtools/session/db-generate-selection.py
diff --git a/client/qldbtools/qldbtools/session1.py b/client/qldbtools/session/db-initial-info.py
similarity index 100%
rename from client/qldbtools/qldbtools/session1.py
rename to client/qldbtools/session/db-initial-info.py
diff --git a/client/qldbtools/qldbtools/session-populate-minio.py b/client/qldbtools/session/db-populate-minio.py
similarity index 100%
rename from client/qldbtools/qldbtools/session-populate-minio.py
rename to client/qldbtools/session/db-populate-minio.py
diff --git a/client/qldbtools/qldbtools/session-post-refine-info.py b/client/qldbtools/session/db-post-refine-info.py
similarity index 97%
rename from client/qldbtools/qldbtools/session-post-refine-info.py
rename to client/qldbtools/session/db-post-refine-info.py
index 4825678..e6e0728 100644
--- a/client/qldbtools/qldbtools/session-post-refine-info.py
+++ b/client/qldbtools/session/db-post-refine-info.py
@@ -1,3 +1,4 @@
+# Session around bin/mc-db-unique
 import qldbtools.utils as utils
 import pandas as pd
 
diff --git a/client/qldbtools/qldbtools/session2.py b/client/qldbtools/session/db-refine-info.py
similarity index 98%
rename from client/qldbtools/qldbtools/session2.py
rename to client/qldbtools/session/db-refine-info.py
index 978da84..7e9e236 100644
--- a/client/qldbtools/qldbtools/session2.py
+++ b/client/qldbtools/session/db-refine-info.py
@@ -1,4 +1,4 @@
-# Experimental work with utils.py, to be merged into it.
+# Experimental work be merged with bin/mc-db-refine-info
 from utils import *
 from pprint import pprint
 
diff --git a/client/qldbtools/qldbtools/session-4-unique.py b/client/qldbtools/session/db-unique-1.py
similarity index 100%
rename from client/qldbtools/qldbtools/session-4-unique.py
rename to client/qldbtools/session/db-unique-1.py
diff --git a/client/qldbtools/session/db-unique.py b/client/qldbtools/session/db-unique.py
new file mode 100644
index 0000000..e6e0728
--- /dev/null
+++ b/client/qldbtools/session/db-unique.py
@@ -0,0 +1,46 @@
+# Session around bin/mc-db-unique
+import qldbtools.utils as utils
+import pandas as pd
+
+#
+#* Collect the information
+#
+df1 = pd.read_csv("scratch/db-info-2.csv")
+
+# Add single uniqueness field -- CID (Cumulative ID) -- using
+# - creationTime
+# - sha
+# - cliVersion
+# - language
+
+from hashlib import blake2b
+
+def cid_hash(row_tuple: tuple):
+    """
+        cid_hash(row_tuple)
+    Take a bytes object and return hash as hex string
+    """
+    h = blake2b(digest_size = 3)
+    h.update(str(row_tuple).encode())
+    # return int.from_bytes(h.digest(), byteorder='big')
+    return h.hexdigest()
+
+# Apply the cid_hash function to the specified columns and create the 'CID' column
+df1['CID'] = df1.apply(lambda row: cid_hash( (row['creationTime'],
+                                              row['sha'], 
+                                              row['cliVersion'], 
+                                              row['language'])
+                                            ), axis=1)
+
+df2 = df1.reindex(columns=['owner', 'name', 'cliVersion', 'creationTime',
+	                       'language', 'sha','CID', 'baselineLinesOfCode', 'path',
+	                       'db_lang', 'db_lang_displayName', 'db_lang_file_count',
+	                       'db_lang_linesOfCode', 'ctime', 'primaryLanguage',
+	                       'finalised', 'left_index', 'size'])
+
+df1['cid']
+
+
+# Local Variables:
+# python-shell-virtualenv-root: "~/work-gh/mrva/mrvacommander/client/qldbtools/venv/"
+# End: