rda-python-common 2.1.11__py3-none-any.whl → 3.0.0__py3-none-any.whl

rda_python_common/PgDBI.py

@@ -17,12 +17,53 @@ import re
 import time
 import hvac
 from datetime import datetime
-import psycopg2 as PgSQL
-from psycopg2.extras import execute_values
-from psycopg2.extras import execute_batch
 from os import path as op
 from . import PgLOG
 
+# Prefer psycopg (v3); fall back to psycopg2 if v3 is not installed.
+try:
+   import psycopg as PgSQL
+   PG_DRIVER = 'psycopg3'
+
+   def execute_values(cursor, sql, argslist, page_size=100):
+      """Compatibility shim for psycopg2.extras.execute_values on psycopg3.
+
+      Rewrites ``VALUES %s`` placeholder to ``VALUES (%s, %s, ...)`` based on
+      the column count inferred from the first row, then dispatches to
+      psycopg3's ``executemany`` (which already batches efficiently).
+      """
+      if not argslist: return
+      ncol = len(argslist[0])
+      row_ph = '(' + ','.join(['%s'] * ncol) + ')'
+      new_sql = re.sub(r'(?i)\bVALUES\s+%s\b', 'VALUES ' + row_ph, sql, count=1)
+      cursor.executemany(new_sql, argslist)
+
+   def execute_batch(cursor, sql, argslist, page_size=100):
+      """Compatibility shim for psycopg2.extras.execute_batch on psycopg3."""
+      cursor.executemany(sql, argslist)
+
+   def get_pgcode(pgerr):
+      """Return SQLSTATE for a psycopg3 error (via err.diag.sqlstate)."""
+      diag = getattr(pgerr, 'diag', None)
+      return getattr(diag, 'sqlstate', None) if diag is not None else None
+
+   def get_pgerror(pgerr):
+      """Return primary error message for a psycopg3 error (via err.diag.message_primary)."""
+      diag = getattr(pgerr, 'diag', None)
+      return getattr(diag, 'message_primary', None) if diag is not None else None
+except ImportError:
+   import psycopg2 as PgSQL
+   from psycopg2.extras import execute_values, execute_batch
+   PG_DRIVER = 'psycopg2'
+
+   def get_pgcode(pgerr):
+      """Return SQLSTATE for a psycopg2 error (via err.pgcode)."""
+      return getattr(pgerr, 'pgcode', None)
+
+   def get_pgerror(pgerr):
+      """Return primary error message for a psycopg2 error (via err.pgerror)."""
+      return getattr(pgerr, 'pgerror', None)
+
 pgdb = None    # reference to a connected database object
 curtran = 0    # 0 - no transaction, 1 - in transaction
 NMISSES = []   # array of mising userno
@@ -439,8 +480,8 @@ def check_dberror(pgerr, pgcnt, sqlstr, ary, logact = PGDBI['ERRLOG']):
 
    ret = PgLOG.FAILURE
 
-   pgcode = pgerr.pgcode
-   pgerror = pgerr.pgerror
+   pgcode = get_pgcode(pgerr)
+   pgerror = get_pgerror(pgerr)
    dberror = "{} {}".format(pgcode, pgerror) if pgcode and pgerror else str(pgerr)
    if pgcnt < PgLOG.PGLOG['DBRETRY']:
       if not pgcode:
@@ -517,7 +558,7 @@ def pgconnect(reconnect = 0, pgcnt = 0, autocommit = True):
       reconnect = 0   # initial connection
 
    while True:
-      config = {'database' : PGDBI['DBNAME'],
+      config = {'dbname' : PGDBI['DBNAME'],
                     'user' : PGDBI['LNNAME']}
       if PGDBI['DBSHOST'] == PgLOG.PGLOG['HOSTNAME']:
          config['host'] = 'localhost'
@@ -526,7 +567,7 @@ def pgconnect(reconnect = 0, pgcnt = 0, autocommit = True):
          if not PGDBI['DBPORT']: PGDBI['DBPORT'] = get_dbport(PGDBI['DBNAME'])
       if PGDBI['DBPORT']: config['port'] = PGDBI['DBPORT']
       config['password'] = '***'
-      sqlstr = "psycopg2.connect(**{})".format(config)
+      sqlstr = "{}.connect(**{})".format(PG_DRIVER, config)
       config['password'] = get_pgpass_password()
       if PgLOG.PGLOG['DBGLEVEL']: PgLOG.pgdbg(1000, sqlstr)
       try:

rda_python_common/PgFile.py

@@ -788,7 +788,7 @@ def delete_backup_file(file, endpoint = None, logact = 0):
    return PgLOG.FAILURE
 
 #
-# reset local file/directory information to make them writable for PgLOG.PGLOG['GDEXUSER']
+# reset local file/directory information to make them writable for PgLOG.PGLOG['COMMONUSER']
 # file - file name (mandatory)
 # info - gathered file info with option 14, None means file not exists
 #

rda_python_common/PgLOG.py

@@ -60,7 +60,7 @@ MISLOG = (0x00811)   # cannot access logfile
 EMLSUM = (0x08000)   # record as email summary
 EMEROL = (0x10000)   # record error as email only
 EMLALL = (0x1D208)   # all email acts
-DOSUDO = (0x20000)   # add 'sudo -u PGLOG['GDEXUSER']'
+DOSUDO = (0x20000)   # add 'sudo -u PGLOG['COMMONUSER']'
 NOTLOG = (0x40000)   # do not log any thing
 OVRIDE = (0x80000)   # do override existing file or record
 NOWAIT = (0x100000)  # do not wait on globus task to finish
@@ -100,9 +100,8 @@ PGLOG = {   # more defined in untaint_suid() with environment variables
    'BACKROOT': "/DRDATA/DECS",  # backup path for desaster recovering tape on hpss
    'OLDAROOT': "/FS/DSS",       # old root path on hpss
    'OLDBROOT': "/DRDATA/DSS",   # old backup tape on hpss
-   'GDEXUSER' : "gdexdata",  # common gdex user name
-   'GDEXEMAIL' : "zji",    # specialist to receipt email intead of common gdex user name
-   'SUDOGDEX' : 0,          # 1 to allow sudo to PGLOG['GDEXUSER']
+   # COMMONUSER and ADMINUSER are set below via SETPGLOG (env overrides PG<KEY>)
+   'SUDOGDEX' : 0,          # 1 to allow sudo to PGLOG['COMMONUSER']
    'HOSTNAME' : '',        # current host name the process in running on
    'OBJCTSTR' : "object",
    'BACKUPNM' : "quasar",
@@ -140,10 +139,22 @@ PGLOG = {   # more defined in untaint_suid() with environment variables
    'EMLPORT' : 25
 }
 
-PGLOG['RDAUSER'] = PGLOG['GDEXUSER']
+def SETPGLOG(key, default):
+   """Set ``PGLOG[key]`` from environment variable ``PG<key>`` or fall back
+   to ``default`` if the variable is unset.  Used to make per-environment
+   overrides (e.g. PGCOMMONUSER, PGADMINUSER) survive package upgrades."""
+   PGLOG[key] = os.environ.get('PG' + key, default)
+
+SETPGLOG("COMMONUSER", "gdexdata")
+SETPGLOG("ADMINUSER", "zji")
+
+PGLOG['RDAUSER'] = PGLOG['COMMONUSER']
 PGLOG['RDAGRP'] = PGLOG['GDEXGRP']
-PGLOG['RDAEMAIL'] = PGLOG['GDEXEMAIL']
+PGLOG['RDAEMAIL'] = PGLOG['ADMINUSER']
 PGLOG['SUDORDA'] = PGLOG['SUDOGDEX']
+# backwards-compat aliases (deprecated: use COMMONUSER / ADMINUSER)
+PGLOG['GDEXUSER'] = PGLOG['COMMONUSER']
+PGLOG['GDEXEMAIL'] = PGLOG['ADMINUSER']
 
 HOSTTYPES = {
    'rda' : 'dsg_mach',
@@ -317,15 +328,15 @@ def send_python_email(subject = None, receiver = None, msg = None, sender = None
    docc = False if cc else True
    if not sender:
       sender = PGLOG['CURUID']
-      if sender != PGLOG['GDEXUSER']: docc = False
-   if sender == PGLOG['GDEXUSER']: sender = PGLOG['GDEXEMAIL']
+      if sender != PGLOG['COMMONUSER']: docc = False
+   if sender == PGLOG['COMMONUSER']: sender = PGLOG['ADMINUSER']
    if sender.find('@') == -1: sender += "@ucar.edu"
    if not receiver:
       receiver = PGLOG['EMLADDR'] if PGLOG['EMLADDR'] else PGLOG['CURUID']
-   if receiver == PGLOG['GDEXUSER']: receiver = PGLOG['GDEXEMAIL']
+   if receiver == PGLOG['COMMONUSER']: receiver = PGLOG['ADMINUSER']
    if receiver.find('@') == -1: receiver += "@ucar.edu"
 
-   if docc and not re.match(PGLOG['GDEXUSER'], sender): add_carbon_copy(sender, 1)
+   if docc and not re.match(PGLOG['COMMONUSER'], sender): add_carbon_copy(sender, 1)
    emlmsg = EmailMessage()
    emlmsg.set_content(msg)
    emlmsg['From'] = sender
@@ -1167,6 +1178,10 @@ def get_command(cmdstr = None):
 
    if not cmdstr: cmdstr = sys.argv[0]
    cmdstr = op.basename(cmdstr)
+   if cmdstr.startswith('setuid_'):
+      euser = pwd.getpwuid(os.geteuid()).pw_name
+      if euser == PGLOG['COMMONUSER']:
+         cmdstr = cmdstr[len('setuid_'):]
    ms = re.match(r'^(.+)\.(py|pl)$', cmdstr)
    if ms:
       return ms.group(1)
@@ -1182,11 +1197,11 @@ def get_local_command(cmd, asuser = None):
    cuser = PGLOG['SETUID'] if PGLOG['SETUID'] else PGLOG['CURUID']
    if not asuser or cuser == asuser: return cmd
 
-   if cuser == PGLOG['GDEXUSER']:
+   if cuser == PGLOG['COMMONUSER']:
       wrapper = "pgstart_" + asuser
       if valid_command(wrapper): return "{} {}".format(wrapper, cmd)
-   elif PGLOG['SUDOGDEX'] and asuser == PGLOG['GDEXUSER']:
-      return "sudo -u {} {}".format(PGLOG['GDEXUSER'], cmd)    # sudo as user gdexdata
+   elif PGLOG['SUDOGDEX'] and asuser == PGLOG['COMMONUSER']:
+      return "sudo -u {} {}".format(PGLOG['COMMONUSER'], cmd)    # sudo as user gdexdata
 
    return cmd
 
@@ -1209,12 +1224,12 @@ def get_hpss_command(cmd, asuser = None, hcmd = None):
    if not hcmd: hcmd = 'hsi'
 
    if asuser and cuser != asuser:
-      if cuser == PGLOG['GDEXUSER']:
+      if cuser == PGLOG['COMMONUSER']:
          return "{} sudo -u {} {}".format(hcmd, asuser, cmd)      # setuid wrapper as user asuser
-      elif PGLOG['SUDOGDEX'] and asuser == PGLOG['GDEXUSER']:
-         return "sudo -u {} {} {}".format(PGLOG['GDEXUSER'], hcmd, cmd)    # sudo as user gdexdata
+      elif PGLOG['SUDOGDEX'] and asuser == PGLOG['COMMONUSER']:
+         return "sudo -u {} {} {}".format(PGLOG['COMMONUSER'], hcmd, cmd)    # sudo as user gdexdata
 
-   if cuser != PGLOG['GDEXUSER']:
+   if cuser != PGLOG['COMMONUSER']:
       if re.match(r'^ls ', cmd) and hcmd == 'hsi':
          return "hpss" + cmd    # use 'hpssls' instead of 'hsi ls'
       elif re.match(r'^htar -tvf', hcmd):
@@ -1231,8 +1246,8 @@ def get_sync_command(host, asuser = None):
 
    host = get_short_host(host)
 
-   if (not (PGLOG['SETUID'] and PGLOG['SETUID'] == PGLOG['GDEXUSER']) and
-      (not asuser or asuser == PGLOG['GDEXUSER'])):
+   if (not (PGLOG['SETUID'] and PGLOG['SETUID'] == PGLOG['COMMONUSER']) and
+      (not asuser or asuser == PGLOG['COMMONUSER'])):
       return "sync" + host
 
    return host + "-sync"
@@ -1246,7 +1261,7 @@ def set_suid(cuid = 0):
    if cuid != PGLOG['EUID'] or cuid != PGLOG['RUID']:
       os.setreuid(cuid, cuid)
       PGLOG['SETUID'] = pwd.getpwuid(cuid).pw_name
-      if not (PGLOG['SETUID'] == PGLOG['GDEXUSER'] or cuid == PGLOG['RUID']):
+      if not (PGLOG['SETUID'] == PGLOG['COMMONUSER'] or cuid == PGLOG['RUID']):
          set_specialist_environments(PGLOG['SETUID'])
          PGLOG['CURUID'] == PGLOG['SETUID']      # set CURUID to a specific specialist
 
@@ -1262,12 +1277,12 @@ def set_common_pglog():
    PGLOG['EUID'] = os.geteuid()
    PGLOG['CURUID'] = pwd.getpwuid(PGLOG['RUID']).pw_name
    try:
-      PGLOG['RDAUID'] = PGLOG['GDEXUID'] = pwd.getpwnam(PGLOG['GDEXUSER']).pw_uid
+      PGLOG['RDAUID'] = PGLOG['GDEXUID'] = pwd.getpwnam(PGLOG['COMMONUSER']).pw_uid
       PGLOG['RDAGID'] = PGLOG['GDEXGID'] = grp.getgrnam(PGLOG['GDEXGRP']).gr_gid
    except:
       PGLOG['RDAUID'] = PGLOG['GDEXUID'] = 0
       PGLOG['RDAGID'] = PGLOG['GDEXGID'] = 0
-   if PGLOG['CURUID'] == PGLOG['GDEXUSER']: PGLOG['SETUID'] = PGLOG['GDEXUSER']
+   if PGLOG['CURUID'] == PGLOG['COMMONUSER']: PGLOG['SETUID'] = PGLOG['COMMONUSER']
 
    PGLOG['HOSTNAME'] = get_host()
    for htype in HOSTTYPES:

rda_python_common/PgOPT.py

@@ -624,7 +624,7 @@ def set_email_logact():
 def validate_dsowner(aname, dsid = None, logname = None, pgds = 0, logact = 0):
 
    if not logname: logname = (params['LN'] if 'LN' in params else PgLOG.PGLOG['CURUID'])
-   if logname == PgLOG.PGLOG['GDEXUSER']: return 1
+   if logname == PgLOG.PGLOG['COMMONUSER']: return 1
 
    dsids = {}
    if dsid:
@@ -1638,7 +1638,7 @@ def send_request_email_notice(pgrqst, errmsg, fcount, rstat, readyfile = None, p
    exclude = (einfo['SENDER'] if errmsg else einfo['RECEIVER'])
    if not errmsg and pgcntl and pgcntl['ccemail']:
       PgLOG.add_carbon_copy(pgcntl['ccemail'], 1, exclude, pgrqst['specialist'])
-   if PgLOG.PGLOG['CURUID'] != pgrqst['specialist'] and PgLOG.PGLOG['CURUID'] != PgLOG.PGLOG['GDEXUSER']:
+   if PgLOG.PGLOG['CURUID'] != pgrqst['specialist'] and PgLOG.PGLOG['CURUID'] != PgLOG.PGLOG['COMMONUSER']:
       PgLOG.add_carbon_copy(PgLOG.PGLOG['CURUID'], 1, exclude)
    if 'CC' in params: PgLOG.add_carbon_copy(params['CC'], 0, exclude)
    einfo['CCD'] = PgLOG.PGLOG['CCDADDR']

rda_python_common/PgSIG.py

@@ -1089,7 +1089,7 @@ def record_background(bcmd, logact = PgLOG.LOGWRN):
       aname = bcmd
 
    mp = r"^\s*(\S+)\s+(\d+)\s+1\s+.*{}(.*)$".format(aname)
-   pc = "ps -u {},{} -f | grep ' 1 ' | grep {}".format(PgLOG.PGLOG['CURUID'], PgLOG.PGLOG['GDEXUSER'], aname)
+   pc = "ps -u {},{} -f | grep ' 1 ' | grep {}".format(PgLOG.PGLOG['CURUID'], PgLOG.PGLOG['COMMONUSER'], aname)
    for i in range(2):
       buf = PgLOG.pgsystem(pc, logact, 20+1024)
       if buf:
@@ -1100,7 +1100,7 @@ def record_background(bcmd, logact = PgLOG.LOGWRN):
             (uid, sbid, acmd) = ms.groups()
             bid = int(sbid)
             if bid in CBIDS: return -1
-            if uid == PgLOG.PGLOG['GDEXUSER']:
+            if uid == PgLOG.PGLOG['COMMONUSER']:
                acmd = re.sub(r'^\.(pl|py)\s+', '', acmd, 1)
             if re.match(r'^{}{}'.format(aname, acmd), bcmd): continue
             CBIDS[bid] = bcmd

rda_python_common/__init__.py

@@ -22,7 +22,7 @@ object that existing callers expect.
 
 from . import PgLOG, PgUtil, PgDBI, PgFile, PgLock, PgCMD, PgSIG, PgOPT, PgSplit
 
-__version__ = "2.1.11"
+__version__ = "3.0.0"
 
 __all__ = [
    "PgLOG",

rda_python_common/pg_dbi.py

@@ -13,24 +13,75 @@ import re
 import time
 import hvac
 from datetime import datetime
-import psycopg2 as PgSQL
-from psycopg2.extras import execute_values
-from psycopg2.extras import execute_batch
 from os import path as op
 from .pg_log import PgLOG
 
+# Driver selection: prefer psycopg (v3) as the default driver; fall back to
+# psycopg2 when psycopg is not installed.  Both drivers share enough surface
+# (connect(**config), Error/OperationalError, cursor.execute/executemany/
+# fetchone/description, connection.commit/rollback/close/autocommit) for this
+# module to use either transparently.
+try:
+   import psycopg as PgSQL
+   PG_DRIVER = 'psycopg3'
+
+   # psycopg3 removed extras.execute_values / extras.execute_batch.
+   # cursor.executemany() in psycopg3 is efficient by default (it uses prepared
+   # statements internally), so the shims below provide matching signatures.
+
+   def execute_values(cursor, sql, argslist, page_size=100):
+      """Driver-neutral shim providing psycopg2.extras.execute_values() on psycopg3.
+
+      Replaces the single ``VALUES %s`` placeholder in ``sql`` (as expected by
+      psycopg2's execute_values) with a per-row ``VALUES (%s, %s, ...)`` tuple
+      built from the first row, then calls ``cursor.executemany()``.  Lets the
+      same call site work under either psycopg (v3) or psycopg2.
+      """
+      if not argslist: return
+      ncol = len(argslist[0])
+      row_ph = '(' + ','.join(['%s']*ncol) + ')'
+      new_sql = re.sub(r'(?i)\bVALUES\s+%s\b', 'VALUES ' + row_ph, sql, count=1)
+      cursor.executemany(new_sql, argslist)
+
+   def execute_batch(cursor, sql, argslist, page_size=100):
+      """Driver-neutral shim providing psycopg2.extras.execute_batch() on psycopg3."""
+      cursor.executemany(sql, argslist)
+
+   def get_pgcode(pgerr):
+      """Return the 5-char SQLSTATE code from a psycopg3 error, or None."""
+      diag = getattr(pgerr, 'diag', None)
+      return getattr(diag, 'sqlstate', None) if diag is not None else None
+
+   def get_pgerror(pgerr):
+      """Return the primary error message from a psycopg3 error, or None."""
+      diag = getattr(pgerr, 'diag', None)
+      return getattr(diag, 'message_primary', None) if diag is not None else None
+except ImportError:
+   import psycopg2 as PgSQL
+   from psycopg2.extras import execute_values, execute_batch
+   PG_DRIVER = 'psycopg2'
+
+   def get_pgcode(pgerr):
+      """Return the 5-char SQLSTATE code from a psycopg2 error, or None."""
+      return getattr(pgerr, 'pgcode', None)
+
+   def get_pgerror(pgerr):
+      """Return the server error message from a psycopg2 error, or None."""
+      return getattr(pgerr, 'pgerror', None)
+
 class PgDBI(PgLOG):
    """PostgreSQL Database Interface layer extending PgLOG.
 
    Provides a high-level API for connecting to and querying PostgreSQL databases
-   using psycopg2. Supports single and batch INSERT, SELECT, UPDATE, and DELETE
-   operations, transaction management, schema introspection, user lookups, usage
-   tracking, and credential retrieval from .pgpass or OpenBao.
+   using psycopg (v3) when available, falling back to psycopg2. Supports single
+   and batch INSERT, SELECT, UPDATE, and DELETE operations, transaction
+   management, schema introspection, user lookups, usage tracking, and
+   credential retrieval from .pgpass or OpenBao.
 
    Inherits all logging and utility helpers from PgLOG.
 
    Instance Attributes:
-      pgdb (connection | None): Active psycopg2 connection, or None when disconnected.
+      pgdb (connection | None): Active psycopg/psycopg2 connection, or None when disconnected.
       curtran (int): Transaction counter: 0 = idle, >0 = inside a transaction.
       NMISSES (list): Cached list of scientist IDs (userno) not found in the DB.
       LMISSES (list): Cached list of login names not found in the DB.
@@ -40,7 +91,8 @@ class PgDBI(PgLOG):
       SYSDOWN (dict): Cache of system-down status records keyed by hostname.
       PGDBI (dict): Active connection and configuration parameters.
       PGSIGNS (list): Special comparison sign tokens recognised by get_field_condition().
-      CHCODE (int): psycopg2 type code for CHAR columns (used to strip trailing spaces).
+      CHCODE (int): Driver type code for CHAR columns (used to strip trailing spaces);
+                    set from psycopg/psycopg2 depending on which driver is in use.
       DBPORTS (dict): Mapping of database names to non-default TCP port numbers.
       DBPASS (dict): Credentials loaded from .pgpass, keyed by (host, port, db, user).
       DBBAOS (dict): Credentials loaded from OpenBao, keyed by database name.
@@ -544,14 +596,15 @@ class PgDBI(PgLOG):
       return tbname
 
    def check_dberror(self, pgerr, pgcnt, sqlstr, ary, logact = None):
-      """Classify a psycopg2 error and decide whether to retry or abort.
+      """Classify a psycopg/psycopg2 error and decide whether to retry or abort.
 
       Handles connection errors (08xxx, 57xxx), lock errors (55xxx), aborted
       transactions (25P02), and missing-table errors (42P01 with ADDTBL flag).
       Retries up to PGLOG['DBRETRY'] times; exits after that threshold.
 
       Args:
-         pgerr (psycopg2.Error): The caught database exception.
+         pgerr (PgSQL.Error): The caught database exception
+                              (psycopg.Error or psycopg2.Error).
          pgcnt (int): Current retry count (0-based).
          sqlstr (str): SQL statement that caused the error, for logging.
          ary: Bound values that were passed to the statement, for logging.
@@ -562,8 +615,8 @@ class PgDBI(PgLOG):
       """
       if logact is None: logact = self.PGDBI['ERRLOG']
       ret = self.FAILURE
-      pgcode = pgerr.pgcode
-      pgerror = pgerr.pgerror
+      pgcode = get_pgcode(pgerr)
+      pgerror = get_pgerror(pgerr)
       dberror = "{} {}".format(pgcode, pgerror) if pgcode and pgerror else str(pgerr)
       if pgcnt < self.PGLOG['DBRETRY']:
          if not pgcode:
@@ -640,15 +693,15 @@ class PgDBI(PgLOG):
          autocommit (bool): Whether to enable autocommit on the new connection.
 
       Returns:
-         connection | int: psycopg2 connection on success, self.FAILURE on error.
+         connection | int: psycopg/psycopg2 connection on success, self.FAILURE on error.
       """
       if self.pgdb:
          if reconnect and not self.pgdb.closed: return self.pgdb    # no need reconnect
       elif reconnect:
          reconnect = 0   # initial connection
       while True:
-         config = {'database': self.PGDBI['DBNAME'],
-                       'user': self.PGDBI['LNNAME']}
+         config = {'dbname': self.PGDBI['DBNAME'],
+                      'user': self.PGDBI['LNNAME']}
          if self.PGDBI['DBSHOST'] == self.PGLOG['HOSTNAME']:
             config['host'] = 'localhost'
          else:
@@ -656,7 +709,7 @@ class PgDBI(PgLOG):
             if not self.PGDBI['DBPORT']: self.PGDBI['DBPORT'] = self.get_dbport(self.PGDBI['DBNAME'])
          if self.PGDBI['DBPORT']: config['port'] = self.PGDBI['DBPORT']
          config['password'] = '***'
-         sqlstr = "psycopg2.connect(**{})".format(config)
+         sqlstr = "{}.connect(**{})".format(PG_DRIVER, config)
          config['password'] = self.get_pgpass_password()
          if self.PGLOG['DBGLEVEL']: self.pgdbg(1000, sqlstr)
          try:
@@ -675,7 +728,7 @@ class PgDBI(PgLOG):
       errors. The search path includes PGDBI['SCPATH'] when it differs from SCNAME.
 
       Returns:
-         cursor | int: psycopg2 cursor on success, self.FAILURE on error.
+         cursor | int: psycopg/psycopg2 cursor on success, self.FAILURE on error.
       """
       pgcur = None
       if not self.pgdb:
@@ -924,7 +977,8 @@ class PgDBI(PgLOG):
       """Insert multiple records into a database table efficiently.
 
       When getid is set, executes individual inserts to capture each returned ID.
-      Otherwise uses psycopg2 execute_values() for a single bulk INSERT.
+      Otherwise uses execute_values() (psycopg2's bulk helper, or the
+      executemany()-based shim on psycopg v3) for a single bulk INSERT.
 
       Args:
          tablename (str): Target table name.
@@ -1365,8 +1419,9 @@ class PgDBI(PgLOG):
    def pgmupdt(self, tablename, records, cnddicts, logact = None):
       """Update multiple rows using parallel value and condition dicts.
 
-      Uses psycopg2 execute_batch() for efficient bulk updates. The number of
-      values in records and cnddicts must match.
+      Uses execute_batch() (psycopg2's bulk helper, or the executemany()-based
+      shim on psycopg v3) for efficient bulk updates. The number of values in
+      records and cnddicts must match.
 
       Args:
          tablename (str): Target table name.
@@ -1508,7 +1563,8 @@ class PgDBI(PgLOG):
    def pgmdel(self, tablename, cnddicts, logact = None):
       """Delete multiple rows using a multi-value condition dict.
 
-      Uses psycopg2 execute_batch() for efficient bulk deletes.
+      Uses execute_batch() (psycopg2's bulk helper, or the executemany()-based
+      shim on psycopg v3) for efficient bulk deletes.
 
       Args:
          tablename (str): Target table name.

rda_python_common/pg_file.py

@@ -987,7 +987,7 @@ class PgFile(PgUtil, PgSIG):
          return self.FINISH
       return self.FAILURE
 
-   # reset local file/directory information to make them writable for self.PGLOG['GDEXUSER']
+   # reset local file/directory information to make them writable for self.PGLOG['COMMONUSER']
    # file - file name (mandatory)
    # info - gathered file info with option 14, None means file not exists
    def reset_local_info(self, file, info = None, logact = 0):

rda_python_common/pg_log.py

@@ -81,7 +81,7 @@ class PgLOG:
    EMLSUM = (0x08000)   # record as email summary
    EMEROL = (0x10000)   # record error as email only
    EMLALL = (0x1D208)   # all email acts
-   DOSUDO = (0x20000)   # add 'sudo -u self.PGLOG['GDEXUSER']'
+   DOSUDO = (0x20000)   # add 'sudo -u self.PGLOG['COMMONUSER']'
    NOTLOG = (0x40000)   # do not log any thing
    OVRIDE = (0x80000)   # do override existing file or record
    NOWAIT = (0x100000)  # do not wait on globus task to finish
@@ -124,9 +124,8 @@ class PgLOG:
          'SETUID': '',         # the login name for suid if it is different to the CURUID
          'FILEMODE': 0o664,    # default 8-base file mode
          'EXECMODE': 0o775,    # default 8-base executable file mode or directory mode
-         'GDEXUSER': "gdexdata",  # common gdex user name
-         'GDEXEMAIL': "zji",    # specialist to receipt email intead of common gdex user name
-         'SUDOGDEX': 0,         # 1 to allow sudo to self.PGLOG['GDEXUSER']
+         # COMMONUSER and ADMINUSER are set below via SETPGLOG (env overrides PG<KEY>)
+         'SUDOGDEX': 0,         # 1 to allow sudo to self.PGLOG['COMMONUSER']
          'HOSTNAME': '',        # current host name the process in running on
          'OBJCTSTR': "object",
          'BACKUPNM': "quasar",
@@ -161,10 +160,6 @@ class PgLOG:
          'EMLSRVR': "ndir.ucar.edu",   # UCAR email server and port
          'EMLPORT': 25
       }
-      self.PGLOG['RDAUSER'] = self.PGLOG['GDEXUSER']
-      self.PGLOG['RDAGRP'] = self.PGLOG['GDEXGRP']
-      self.PGLOG['RDAEMAIL'] = self.PGLOG['GDEXEMAIL']
-      self.PGLOG['SUDORDA'] = self.PGLOG['SUDOGDEX']
       self.HOSTTYPES = {
          'rda': 'dsg_mach',
          'crlogin': 'dav',
@@ -188,6 +183,13 @@ class PgLOG:
       self.set_common_pglog()
       self.OUTPUT = None
 
+   def SETPGLOG(self, key, default):
+      """Set ``self.PGLOG[key]`` from environment variable ``PG<key>`` or
+      fall back to ``default`` if the variable is unset.  Used to make
+      per-environment overrides (e.g. PGCOMMONUSER, PGADMINUSER) survive
+      package upgrades."""
+      self.PGLOG[key] = os.environ.get('PG' + key, default)
+
    def open_output(self, outfile=None):
       """Open the result output destination.
 
@@ -392,14 +394,14 @@ class PgLOG:
       docc = False if cc else True
       if not sender:
          sender = self.PGLOG['CURUID']
-         if sender != self.PGLOG['GDEXUSER']: docc = False
-      if sender == self.PGLOG['GDEXUSER']: sender = self.PGLOG['GDEXEMAIL']
+         if sender != self.PGLOG['COMMONUSER']: docc = False
+      if sender == self.PGLOG['COMMONUSER']: sender = self.PGLOG['ADMINUSER']
       if sender.find('@') == -1: sender += "@ucar.edu"
       if not receiver:
          receiver = self.PGLOG['EMLADDR'] if self.PGLOG['EMLADDR'] else self.PGLOG['CURUID']
-      if receiver == self.PGLOG['GDEXUSER']: receiver = self.PGLOG['GDEXEMAIL']
+      if receiver == self.PGLOG['COMMONUSER']: receiver = self.PGLOG['ADMINUSER']
       if receiver.find('@') == -1: receiver += "@ucar.edu"
-      if docc and not re.match(self.PGLOG['GDEXUSER'], sender): self.add_carbon_copy(sender, 1)
+      if docc and not re.match(self.PGLOG['COMMONUSER'], sender): self.add_carbon_copy(sender, 1)
       emlmsg = EmailMessage()
       emlmsg.set_content(msg)
       emlmsg['From'] = sender
@@ -1324,10 +1326,17 @@ class PgLOG:
                self.PGLOG['PGBATCH'] = ''
                self.PGLOG['CURBID'] = 0
 
-   @staticmethod
-   def get_command(cmdstr=None):
+   def get_command(self, cmdstr=None):
       """Return the base command name, stripping directory and ``.py``/``.pl`` extension.
 
+      When invoked via the pywrapper setuid C wrapper, ``sys.argv[0]`` is the
+      resolved Python script path (e.g. ``/.../setuid_rdacp``) rather than the
+      alias the user typed (e.g. ``rdacp``); the kernel discards argv[0] when
+      handling the script's shebang.  When the basename starts with
+      ``setuid_`` and the effective user equals ``self.PGLOG['COMMONUSER']``,
+      this process was started via pywrapper, so the ``setuid_`` prefix is
+      stripped to recover the logical command name.
+
       Args:
           cmdstr: Path string.  Defaults to ``sys.argv[0]``.
 
@@ -1336,6 +1345,10 @@ class PgLOG:
       """
       if not cmdstr: cmdstr = sys.argv[0]
       cmdstr = op.basename(cmdstr)
+      if cmdstr.startswith('setuid_'):
+         euser = pwd.getpwuid(os.geteuid()).pw_name
+         if euser == self.PGLOG['COMMONUSER']:
+            cmdstr = cmdstr[len('setuid_'):]
       ms = re.match(r'^(.+)\.(py|pl)$', cmdstr)
       if ms:
          return ms.group(1)
@@ -1358,11 +1371,11 @@ class PgLOG:
       """
       cuser = self.PGLOG['SETUID'] if self.PGLOG['SETUID'] else self.PGLOG['CURUID']
       if not asuser or cuser == asuser: return cmd
-      if cuser == self.PGLOG['GDEXUSER']:
+      if cuser == self.PGLOG['COMMONUSER']:
          wrapper = "pgstart_" + asuser
          if self.valid_command(wrapper): return "{} {}".format(wrapper, cmd)
-      elif self.PGLOG['SUDOGDEX'] and asuser == self.PGLOG['GDEXUSER']:
-         return "sudo -u {} {}".format(self.PGLOG['GDEXUSER'], cmd)    # sudo as user gdexdata
+      elif self.PGLOG['SUDOGDEX'] and asuser == self.PGLOG['COMMONUSER']:
+         return "sudo -u {} {}".format(self.PGLOG['COMMONUSER'], cmd)    # sudo as user gdexdata
       return cmd
 
    def get_remote_command(self, cmd, host, asuser=None):
@@ -1389,8 +1402,8 @@ class PgLOG:
           Sync command string (e.g. ``"synccasper"`` or ``"casper-sync"``).
       """
       host = self.get_short_host(host)
-      if (not (self.PGLOG['SETUID'] and self.PGLOG['SETUID'] == self.PGLOG['GDEXUSER']) and
-         (not asuser or asuser == self.PGLOG['GDEXUSER'])):
+      if (not (self.PGLOG['SETUID'] and self.PGLOG['SETUID'] == self.PGLOG['COMMONUSER']) and
+         (not asuser or asuser == self.PGLOG['COMMONUSER'])):
          return "sync" + host
       return host + "-sync"
 
@@ -1407,7 +1420,7 @@ class PgLOG:
       if cuid != self.PGLOG['EUID'] or cuid != self.PGLOG['RUID']:
          os.setreuid(cuid, cuid)
          self.PGLOG['SETUID'] = pwd.getpwuid(cuid).pw_name
-         if not (self.PGLOG['SETUID'] == self.PGLOG['GDEXUSER'] or cuid == self.PGLOG['RUID']):
+         if not (self.PGLOG['SETUID'] == self.PGLOG['COMMONUSER'] or cuid == self.PGLOG['RUID']):
             self.set_specialist_environments(self.PGLOG['SETUID'])
             self.PGLOG['CURUID'] == self.PGLOG['SETUID']      # set CURUID to a specific specialist
 
@@ -1421,18 +1434,28 @@ class PgLOG:
 
       Called automatically by :meth:`__init__`.
       """
-      self.PGLOG['CURDIR'] = os.getcwd()   
+      # resolve common/admin user from environment (PGCOMMONUSER / PGADMINUSER)
+      self.SETPGLOG("COMMONUSER", "gdexdata")
+      self.SETPGLOG("ADMINUSER", "zji")
+      self.PGLOG['RDAUSER'] = self.PGLOG['COMMONUSER']
+      self.PGLOG['RDAGRP'] = self.PGLOG['GDEXGRP']
+      self.PGLOG['RDAEMAIL'] = self.PGLOG['ADMINUSER']
+      self.PGLOG['SUDORDA'] = self.PGLOG['SUDOGDEX']
+      # backwards-compat aliases (deprecated: use COMMONUSER / ADMINUSER)
+      self.PGLOG['GDEXUSER'] = self.PGLOG['COMMONUSER']
+      self.PGLOG['GDEXEMAIL'] = self.PGLOG['ADMINUSER']
+      self.PGLOG['CURDIR'] = os.getcwd()
       # set current user id
       self.PGLOG['RUID'] = os.getuid()
       self.PGLOG['EUID'] = os.geteuid()
       self.PGLOG['CURUID'] = pwd.getpwuid(self.PGLOG['RUID']).pw_name
       try:
-         self.PGLOG['RDAUID'] = self.PGLOG['GDEXUID'] = pwd.getpwnam(self.PGLOG['GDEXUSER']).pw_uid
+         self.PGLOG['RDAUID'] = self.PGLOG['GDEXUID'] = pwd.getpwnam(self.PGLOG['COMMONUSER']).pw_uid
          self.PGLOG['RDAGID'] = self.PGLOG['GDEXGID'] = grp.getgrnam(self.PGLOG['GDEXGRP']).gr_gid
       except KeyError:
          self.PGLOG['RDAUID'] = self.PGLOG['GDEXUID'] = 0
          self.PGLOG['RDAGID'] = self.PGLOG['GDEXGID'] = 0
-      if self.PGLOG['CURUID'] == self.PGLOG['GDEXUSER']: self.PGLOG['SETUID'] = self.PGLOG['GDEXUSER']   
+      if self.PGLOG['CURUID'] == self.PGLOG['COMMONUSER']: self.PGLOG['SETUID'] = self.PGLOG['COMMONUSER']   
       self.PGLOG['HOSTNAME'] = self.get_host()
       for htype in self.HOSTTYPES:
          ms = re.match(r'^{}(-|\d|$)'.format(htype), self.PGLOG['HOSTNAME'])

rda_python_common/pg_opt.py

@@ -649,7 +649,7 @@ class PgOPT(PgFile):
          dataset in params), or logs a fatal error and exits.
       """
       if not logname: logname = (self.params['LN'] if 'LN' in self.params else self.PGLOG['CURUID'])
-      if logname == self.PGLOG['GDEXUSER']: return 1
+      if logname == self.PGLOG['COMMONUSER']: return 1
       dsids = {}
       if dsid:
          dsids[dsid] = 1
@@ -1847,7 +1847,7 @@ class PgOPT(PgFile):
       exclude = (einfo['SENDER'] if errmsg else einfo['RECEIVER'])
       if not errmsg and pgcntl and pgcntl['ccemail']:
          self.add_carbon_copy(pgcntl['ccemail'], 1, exclude, pgrqst['specialist'])
-      if self.PGLOG['CURUID'] != pgrqst['specialist'] and self.PGLOG['CURUID'] != self.PGLOG['GDEXUSER']:
+      if self.PGLOG['CURUID'] != pgrqst['specialist'] and self.PGLOG['CURUID'] != self.PGLOG['COMMONUSER']:
          self.add_carbon_copy(self.PGLOG['CURUID'], 1, exclude)
       if 'CC' in self.params: self.add_carbon_copy(self.params['CC'], 0, exclude)
       einfo['CCD'] = self.PGLOG['CCDADDR']

rda_python_common/pg_sig.py

@@ -1183,14 +1183,14 @@ class PgSIG(PgDBI):
       ms = re.match(r'^(\S+)', bcmd)
       aname = ms.group(1) if ms else bcmd
       curuid = self.PGLOG['CURUID']
-      gdexuser = self.PGLOG['GDEXUSER']
+      commonuser = self.PGLOG['COMMONUSER']
       for i in range(2):
          for proc in psutil.process_iter(['pid', 'ppid', 'username', 'cmdline']):
             try:
                info = proc.info
                if info.get('ppid') != 1: continue
                uid = info.get('username')
-               if uid != curuid and uid != gdexuser: continue
+               if uid != curuid and uid != commonuser: continue
                cmdline = info.get('cmdline') or []
                if not cmdline: continue
                line = ' '.join(cmdline)
@@ -1199,7 +1199,7 @@ class PgSIG(PgDBI):
                bid = info['pid']
                if bid in self.CBIDS: return -1
                acmd = line[idx+len(aname):]
-               if uid == gdexuser:
+               if uid == commonuser:
                   acmd = re.sub(r'^\.(pl|py)\s+', '', acmd, 1)
                if re.match(r'^{}{}'.format(aname, acmd), bcmd): continue
                self.CBIDS[bid] = bcmd

rda_python_common/pg_util.py

@@ -14,6 +14,8 @@ import time
 import datetime
 import calendar
 import glob
+import bisect
+import functools
 from os import path as op
 from .pg_log import PgLOG
 
@@ -419,11 +421,7 @@ class PgUtil(PgLOG):
          list: Mixed int/str parts of the split datetime.
       """
       if not isinstance(sdt, str): sdt = str(sdt)
-      adt = re.split(sep, sdt)
-      acnt = len(adt)
-      for i in range(acnt):
-         if adt[i].isdigit(): adt[i] = int(adt[i])
-      return adt
+      return [int(x) if x.isdigit() else x for x in re.split(sep, sdt)]
 
    #    date: given date in format of fromfmt
    #   tofmt: date formats; ex. "Month D, YYYY"
@@ -547,14 +545,8 @@ class PgUtil(PgLOG):
       # adjust second/minute/hour values out of range
       for i in range(3):
          if tms[i] != None and tms[i+1] != None:
-            if tms[i] < 0:
-               while tms[i] < 0:
-                  tms[i] += ups[i]
-                  tms[i+1] -= 1
-            elif tms[i] >= ups[i]:
-               while tms[i] >= ups[i]:
-                  tms[i] -= ups[i]
-                  tms[i+1] += 1
+            carry, tms[i] = divmod(tms[i], ups[i])
+            tms[i+1] += carry
       sdt = self.fmtdate(yr, mn, dy, tofmt)
       # format second/minute/hour values
       for i in range(3):
@@ -592,14 +584,8 @@ class PgUtil(PgLOG):
       """
       if not tofmt: tofmt = "YYYY-MM-DD:HH"
       if hr != None and dy != None:   # adjust hour value out of range
-         if hr < 0:
-            while hr < 0:
-               hr += 24
-               dy -= 1
-         elif hr > 23:
-            while hr > 23:
-               hr -= 24
-               dy += 1
+         carry, hr = divmod(hr, 24)
+         dy += carry
       datehour = self.fmtdate(yr, mn, dy, tofmt)
       if hr != None:
          ms = re.search(self.DATEFMTS['H'], datehour, re.I)
@@ -733,9 +719,8 @@ class PgUtil(PgLOG):
       """
       if not sdt: return [None, None]
       if not isinstance(sdt, str): sdt = str(sdt)
-      adt = re.split(' ', sdt)
-      acnt = len(adt)
-      if acnt == 1: adt.append('00:00:00')
+      adt = sdt.split(' ')
+      if len(adt) == 1: adt.append('00:00:00')
       return adt
 
    # convert given date/time to unix epoch time; -1 if cannot
@@ -1209,10 +1194,8 @@ class PgUtil(PgLOG):
       cnt2 = len(lst2)
       if unique:
          for i in range(cnt2):
-            for j in range(cnt1):
-               if PgUtil.pgcmp(lst1[j], lst2[i]) != 0: break
-            if j >= cnt1:
-              lst1.append(lst2[i])
+            if lst2[i] not in lst1:
+               lst1.append(lst2[i])
       else:
          lst1.extend(lst2)
       return lst1
@@ -1312,7 +1295,8 @@ class PgUtil(PgLOG):
             rec.append(val)
          rec.append(i)   # add column to cache the row index
          srecs.append(rec)
-      srecs = self.quicksort(srecs, 0, count-1, desc, fcnt, nums)
+      srecs.sort(key=functools.cmp_to_key(
+         lambda a, b: PgUtil.cmp_records(a, b, desc, fcnt, nums)))
       # sort pgrecs according the cached row index column in ordered srecs
       rets = {}
       for fld in pgrecs:
@@ -1335,10 +1319,13 @@ class PgUtil(PgLOG):
       Returns:
          int: Positive when date1 > date2, negative when date1 < date2.
       """
-      ut1 = ut2 = 0
-      if date1: ut1 = PgUtil.unixtime(date1)
-      if date2: ut2 = PgUtil.unixtime(date2)
-      return round((ut1 - ut2)/86400)   # 24*60*60
+      epoch = datetime.date(1970, 1, 1)
+      def _to_date(d):
+         if not d: return epoch
+         ms = re.match(r'^(\d+)-(\d+)-(\d+)', str(d))
+         if not ms: return epoch
+         return datetime.date(int(ms.group(1)), int(ms.group(2)), int(ms.group(3)))
+      return (_to_date(date1) - _to_date(date2)).days
 
    # Return: the number of seconds bewteen time1 and time2
    @staticmethod
@@ -1557,15 +1544,10 @@ class PgUtil(PgLOG):
       if ms:
          (syr, smn) = ms.groups()
          nyr = int(syr) + yr
-         nmn = int(smn) + mn
-         if nmn < 0:
-            while nmn < 0:
-               nyr -= 1
-               nmn += 12
-         else:
-            while nmn > 12:
-               nyr += 1
-               nmn -= 12
+         nmn = int(smn) + mn - 1   # shift to 0-indexed for divmod
+         extra, nmn = divmod(nmn, 12)
+         nyr += extra
+         nmn += 1                  # back to 1-indexed
          ym = "{:04}{:02}".format(nyr, nmn)
       return ym
 
@@ -1729,14 +1711,7 @@ class PgUtil(PgLOG):
       if ms:
          shr = ms.group(1)
          hr = int(shr) + nhour
-         if hr < 0:
-            while hr < 0:
-               dy -= 1
-               hr += 24
-         else:
-            while hr > 23:
-               dy += 1
-               hr -= 24
+         dy, hr = divmod(hr, 24)
       shour = "{:02}".format(hr)
       if shr != shour: stime = re.sub(shr, shour, stime, 1)
       if dy: sdate = self.adddate(sdate, 0, 0, dy)
@@ -1765,14 +1740,8 @@ class PgUtil(PgLOG):
          if nhour != None:
             if isinstance(nhour, str): nhour = int(nhour)
             hr += nhour
-         if hr < 0:
-            while hr < 0:
-               dy -= 1
-               hr += 24
-         else:
-            while hr > 23:
-               dy += 1
-               hr -= 24
+         carry, hr = divmod(hr, 24)
+         dy += carry
          if nhour != None: nhour = hr
       if yr or mn or dy: sdate = self.adddate(sdate, yr, mn, dy)
       return [sdate, nhour]
@@ -1799,7 +1768,7 @@ class PgUtil(PgLOG):
          str: Resulting datetime string in 'YYYY-MM-DD HH:MM:SS' format.
       """
       if sdatetime and not isinstance(sdatetime, str): sdatetime = str(sdatetime)
-      (sdate, stime) = re.split(' ', sdatetime)
+      (sdate, stime) = sdatetime.split(' ', 1)
       if hh or nn or ss: (sdate, stime) = self.addtime(sdate, stime, hh, nn, ss)
       if nf:
          sdate = self.addmonth(sdate, mm, nf)
@@ -1837,14 +1806,8 @@ class PgUtil(PgLOG):
             tms[1] += int(ms.group(2))
             tms[0] += int(ms.group(3))
       for i in range(3):
-         if tms[i] < 0:
-            while tms[i] < 0:
-               tms[i] += ups[i]
-               tms[i+1] -= 1
-         elif tms[i] >= ups[i]:
-            while tms[i] >= ups[i]:
-               tms[i] -= ups[i]
-               tms[i+1] += 1
+         carry, tms[i] = divmod(tms[i], ups[i])
+         tms[i+1] += carry
       stime = "{:02}:{:02}:{:02}".format(tms[2], tms[1], tms[0])
       if tms[3]: sdate = self.adddate(sdate, 0, 0, tms[3])
       return [sdate, stime]
@@ -1985,7 +1948,7 @@ class PgUtil(PgLOG):
       """
       if sdatetime and not isinstance(sdatetime, str): sdatetime = str(sdatetime)
       if not (unit and unit in 'YMWDHNS'): return sdatetime
-      (sdate, stime) = re.split(' ', sdatetime)
+      (sdate, stime) = sdatetime.split(' ', 1)
       if unit in 'HNS':
          stime = self.endtime(stime, unit)
       else:
@@ -2011,7 +1974,7 @@ class PgUtil(PgLOG):
       for val in values:
          if val is None: continue
          sval = str(val)
-         if sval and not re.search(r'\n', sval):
+         if sval and '\n' not in sval:
             slen = len(sval)
             if slen > clen: clen = slen
       return clen
@@ -2199,21 +2162,8 @@ class PgUtil(PgLOG):
       Returns:
          int: Index of the matching element, or -1 when not found.
       """
-      ret = -1
-      if (hidx - lidx) < 11:   # use linear search for less than 11 items
-         for midx in range(lidx, hidx):
-            if key == list[midx]:
-               ret = midx
-               break
-      else:
-         midx = (lidx + hidx) // 2
-         if key == list[midx]:
-            ret = midx
-         elif key < list[midx]:
-            ret = PgUtil.asearch(lidx, midx, key, list)
-         else:
-            ret = PgUtil.asearch(midx + 1, hidx, key, list)
-      return ret
+      idx = bisect.bisect_left(list, key, lidx, hidx)
+      return idx if idx < hidx and list[idx] == key else -1
 
    #   lidx: lower index limit  (including)
    #   hidx: higher index limit (excluding)
@@ -2362,14 +2312,11 @@ class PgUtil(PgLOG):
             buffer = f.read(blocksize)
          # Check for null bytes (a strong indicator of a binary file)
          if not buffer or b'\0' in buffer: return 0
-         text_characters = (
+         text_set = frozenset(
             b'\t\n\r\f\v' +        # Whitespace characters
             bytes(range(32, 127))  # Printable ASCII characters
          )
-         non_text_count = 0
-         for byte in buffer:
-            if byte not in text_characters:
-               non_text_count += 1  # Count non-text characters
+         non_text_count = sum(b not in text_set for b in buffer)
          # If a significant portion of the buffer consists of non-text characters,
          # it's likely a binary file.
          return 1 if((non_text_count/len(buffer)) < threshhold) else 0

{rda_python_common-2.1.11.dist-info → rda_python_common-3.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rda_python_common
-Version: 2.1.11
+Version: 3.0.0
 Summary: RDA Python common library codes shared by other RDA python packages
 Author-email: Zaihua Ji <zji@ucar.edu>
 Project-URL: Homepage, https://github.com/NCAR/rda-python-common
@@ -11,23 +11,45 @@ Classifier: Development Status :: 5 - Production/Stable
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: psycopg2-binary
+Requires-Dist: psycopg
 Requires-Dist: psutil
 Requires-Dist: rda-python-globus
 Requires-Dist: unidecode
 Requires-Dist: hvac
+Provides-Extra: psycopg2
+Requires-Dist: psycopg2; extra == "psycopg2"
+Provides-Extra: psycopg2-binary
+Requires-Dist: psycopg2-binary; extra == "psycopg2-binary"
 Dynamic: license-file
 
 # rda-python-common
 
 Python common library codes to be shared by other RDA python utility programs.
 
-## Installing and using in another RDA python repo
+## Environment setup
 
-`rda-python-common` is the foundation that every other `rda-python-*` repo
-builds on.  To consume it from a new or existing repo, follow these steps.
+Create a Python environment first; the install command in the next section
+runs inside whichever environment you activate here.
+
+### Option A — Python venv (DECS machines)
+
+```bash
+python3 -m venv $ENVHOME          # e.g. /glade/u/home/gdexdata/gdexmsenv
+source $ENVHOME/bin/activate
+```
+
+### Option B — Conda (DAV/Casper)
 
-### 1. Install the package
+```bash
+conda create --prefix $ENVHOME python=3.12   # e.g. /glade/work/gdexdata/conda-envs/pg-gdex
+conda activate $ENVHOME
+```
+
+## Installing rda-python-common
+
+Pick whichever install mode fits your workflow.  All four pull in the
+transitive dependencies (`psycopg`, `rda-python-globus`, `unidecode`,
+`hvac`) automatically.
 
 For local development, clone this repo alongside your project and install it
 in editable mode so that changes are picked up without re-installing:
@@ -38,6 +60,15 @@ cd rda-python-common
 pip install -e .
 ```
 
+To test a specific branch (e.g. an in-progress feature or fix branch), pass
+`-b/--branch` to `git clone`:
+
+```bash
+git clone -b <branch-name> https://github.com/NCAR/rda-python-common.git
+cd rda-python-common
+pip install -e .
+```
+
 For a regular (non-editable) install from a checkout:
 
 ```bash
@@ -50,10 +81,75 @@ For a production install on a system that uses the published distribution:
 pip install rda_python_common
 ```
 
-The package brings in its own transitive dependencies (`psycopg2-binary`,
-`rda-python-globus`, `unidecode`, `hvac`).
+### PostgreSQL driver: psycopg v3 (default) and psycopg2 (fallback)
+
+`rda-python-common` uses **psycopg v3** by default.  `pg_dbi.py`
+auto-detects which driver is installed at import time and prefers psycopg v3
+when both are present; no code changes are needed to switch drivers.
 
-### 2. Declare it as a dependency in your project
+The required dependency is the base `psycopg` package, which works whether
+psycopg was compiled from source or installed via a binary wheel.  If psycopg
+is not available on your system, install whichever driver works:
+
+```bash
+pip install psycopg || pip install psycopg2
+```
+
+To explicitly install the legacy psycopg2 driver:
+
+```bash
+pip install "rda_python_common[psycopg2]"          # build from source
+pip install "rda_python_common[psycopg2-binary]"   # pre-built wheel
+```
+
+## Configuration: COMMONUSER and ADMINUSER
+
+`PGLOG['COMMONUSER']` is the shared common user that setuid-wrapped programs
+execute as (default `gdexdata`), and `PGLOG['ADMINUSER']` is the admin
+specialist user that receives email notifications and is permitted to invoke
+`pgstart_<user>` (default `zji`).
+
+Both values are initialized via the `SETPGLOG(key, default)` helper, which
+reads the environment variable `PG<KEY>` and falls back to the supplied
+default when the variable is unset:
+
+```python
+# pg_log.py (class-based)
+self.SETPGLOG("COMMONUSER", "gdexdata")   # reads $PGCOMMONUSER
+self.SETPGLOG("ADMINUSER",  "zji")        # reads $PGADMINUSER
+
+# PgLOG.py (module-level) exposes the same helper as a function
+SETPGLOG("COMMONUSER", "gdexdata")
+SETPGLOG("ADMINUSER",  "zji")
+```
+
+To override the defaults per environment **once** so the values persist
+across `pip install --upgrade`, set the environment variables:
+
+```bash
+export PGCOMMONUSER=gdexdata    # overrides PGLOG['COMMONUSER']
+export PGADMINUSER=zji          # overrides PGLOG['ADMINUSER']
+```
+
+Place these `export` lines in `$ENVHOME/bin/activate` (venv), or set them as
+conda environment variables so they are applied whenever the environment is
+activated:
+
+```bash
+conda env config vars set PGCOMMONUSER=gdexdata PGADMINUSER=zji
+conda activate $ENVHOME   # reactivate to pick up the values
+```
+
+If the variables are unset, the built-in defaults (`gdexdata` / `zji`) are
+used, preserving existing behavior.
+
+## Using rda-python-common in another RDA python repo
+
+`rda-python-common` is the foundation that every other `rda-python-*` repo
+builds on.  Once it is installed in the active environment, consuming it from
+a new or existing repo takes three short steps.
+
+### 1. Declare it as a dependency in your project
 
 Add `rda_python_common` to the `dependencies` list of your project's
 `pyproject.toml` so that downstream installs pull it in automatically:
@@ -72,9 +168,10 @@ This is the same pattern used by `rda-python-dsarch`, `rda-python-dsupdt`,
 `rda-python-dsrqst`, `rda-python-dscheck`, `rda-python-metrics`, and
 `rda-python-miscs`.
 
-### 3. Import the modules you need
+### 2. Import the modules you need
 
-Two import styles are supported (see [Usage examples](#usage-examples) below):
+Two import styles are supported (see [Usage examples](#usage-examples) below
+for fuller patterns):
 
 ```python
 # Preferred for new code -- import the class from the lower-case module
@@ -86,26 +183,26 @@ from rda_python_common import PgLOG, PgDBI
 PgLOG.pglog("hello", PgLOG.LOGWRN)
 ```
 
-### 4. Verify the install
+### 3. Verify the install
 
 ```bash
 python -c "import rda_python_common; print(rda_python_common.__version__)"
 ```
 
-You should see the installed version (currently `2.1.11`).  If the import
+You should see the installed version (currently `3.0.0`).  If the import
 fails, double-check that the active Python environment is the one where you
 ran `pip install`.
 
 ## Modules
 
-All shared functionality lives under `src/rda_python_common/` and is organised as
-a single-inheritance class hierarchy.  Each module defines exactly one class;
-later classes extend earlier ones, so an application that instantiates the
-top-of-chain class (typically `PgOPT` or `PgCMD`) gets every helper through one
-object.
+All shared functionality lives under `src/rda_python_common/` and is organised
+as a (mostly) single-inheritance class hierarchy.  Each module defines exactly
+one class; later classes extend earlier ones, so an application that
+instantiates the top-of-chain class (typically `PgOPT` or `PgCMD`) gets every
+helper through one object.
 
-Inheritance tree (top-down; multi-inheritance shown as two arrows
-converging on the same child):
+The inheritance tree below is read top-down; the two multi-inheritance joins
+are shown as two arrows converging on the same child:
 
 ```
                           PgLOG
@@ -142,6 +239,8 @@ The tree is single inheritance everywhere except at two join points:
   operations (`PgDBI`) it needs to keep the shared `wfile` table and the
   per-dataset `wfile_<dsid>` partitions in sync.
 
+Each class lives in its own module.  Walking the tree from the root:
+
 - **`pg_log.py`** — `PgLOG`.  Root of the hierarchy.  Provides the central
   logging facility (bit-mask `logact` flags such as `MSGLOG`, `WARNLG`,
   `ERRLOG`, `EXITLG`), e-mail dispatch, system-command execution, process
@@ -165,7 +264,8 @@ The tree is single inheritance everywhere except at two join points:
   long-running batch jobs coordinate cleanly.
 
 - **`pg_dbi.py`** — `PgDBI(PgLOG)`.  PostgreSQL database interface built on
-  `psycopg2`.  Wraps connection management, batch `INSERT`/`SELECT`/
+  `psycopg` (v3 by default, with `psycopg2` as an opt-in fallback).  Wraps
+  connection management, batch `INSERT`/`SELECT`/
   `UPDATE`/`DELETE`, transaction control, and credential lookup from
   `.pgpass` or OpenBao.  All RDA tools talk to the `rdadb` database through
   this class.
@@ -199,9 +299,9 @@ The tree is single inheritance everywhere except at two join points:
 
 ## Usage examples
 
-Each class lives in its own submodule.  Import the class you need, then
-either instantiate it directly or subclass it to add application-specific
-state and methods.
+The patterns below show the typical ways the classes above are used in
+practice.  Import the class you need, then either instantiate it directly or
+subclass it to add application-specific state and methods.
 
 ### 1. Direct instantiation — use the helpers as-is
 

rda_python_common-3.0.0.dist-info/RECORD

@@ -0,0 +1,28 @@
+rda_python_common/PgCMD.py,sha256=EYjG2Z4zEnvsXE1z-jt5UaNoEKxnOYYiMMzvW6HrKA4,20597
+rda_python_common/PgDBI.py,sha256=PEpZ5DyUuLf-xtdtXdovKxdrNAMkCTHXXH7BUyosp9M,78129
+rda_python_common/PgFile.py,sha256=y_Gxi-54cyb1jpJRKNl3OlOm8I3WG7JuvgANWJ7PDE8,99372
+rda_python_common/PgLOG.py,sha256=l6PXrgCPZ_tmYKSEufoHfWBfCBzVuwcHXpbk3aYA7_w,55892
+rda_python_common/PgLock.py,sha256=12i84nsGBuifSyPnm8IR63LvHvRuVU573D5QKFlHdOI,22623
+rda_python_common/PgOPT.py,sha256=tJ8qb2515HaMPR-oLIg8BKalI1BxcmIHcSb0UEYx2K4,56248
+rda_python_common/PgSIG.py,sha256=dVENQ6tvnoa8fSZ8sYenMP4IVKExtU7fdSdKhSLxlWE,35807
+rda_python_common/PgSplit.py,sha256=SSg5_Qu5PqP44EkqebO-V_cErNcdE2QtORgFHQ7RqlQ,8822
+rda_python_common/PgUtil.py,sha256=OqESKCd72b9g8m8jwjPJhXDtPYlW6G8oSOhwChvz2Cg,48600
+rda_python_common/__init__.py,sha256=WTpasPcnTQMDxRbPXv6vTbQQv8bITdUSkZ_RfdyBtig,994
+rda_python_common/pg_cmd.py,sha256=PiQaAeb7l92LceqMwSzLpz9nD5pDRHJcEZxTDn-HeCs,33255
+rda_python_common/pg_dbi.py,sha256=DxteZzGLbyvM4yNWkWibv9QYaNheMNv4ybs01bVgoiQ,118959
+rda_python_common/pg_file.py,sha256=nwu1DTD6Pgi4yUFt_IJwvYvMbVMW1eEIf1N5EZjM1o8,162232
+rda_python_common/pg_lock.py,sha256=31EaVDjCkcx3-n8-KnzG18R8Pz7Z6KyFsEqcml6Iq5c,32702
+rda_python_common/pg_log.py,sha256=lzhjEL7FaGjHfl4cmlMuIZVAb5x0fSgiI8AShe0sAHw,82146
+rda_python_common/pg_opt.py,sha256=evf0ZtNeYyRjGyTIghD6wI5u7eDbiDkDudLYRk5z0QA,82500
+rda_python_common/pg_password.py,sha256=X-eIDwdqBhtrhrbDTNWle-0JtWsyIVZdDOZaBu7cFHM,2343
+rda_python_common/pg_sig.py,sha256=o4L9qjrgOIAASXntY6kHfEGV2TXuFL3mTczqkemY9oQ,53572
+rda_python_common/pg_split.py,sha256=aAWKUZPmZ-LQ_fJ3DSKzPKxJw0fMDJ2fgP8ZT629M30,16375
+rda_python_common/pg_util.py,sha256=3_-baqCI9j5bkC2Uw3hRJZtYwdr0FQC6mtgbeIhLwyQ,86045
+rda_python_common/pgpassword.py,sha256=aTQaO59QokWrv2EKom4TvKhNW2Mr6aFMMBVG4DCbcKI,5023
+rda_python_common/pgpassword.usg,sha256=Wrle6A8sdlMGx3ZEAmE6TNDPOlG84Whe0T3rCNFzPfY,2013
+rda_python_common-3.0.0.dist-info/licenses/LICENSE,sha256=1dck4EAQwv8QweDWCXDx-4Or0S8YwiCstaso_H57Pno,1097
+rda_python_common-3.0.0.dist-info/METADATA,sha256=Gy2zqPkeWIe7dXTjv-sz62JbAXSCJGOyJM1HKjVS0hA,14528
+rda_python_common-3.0.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+rda_python_common-3.0.0.dist-info/entry_points.txt,sha256=pZgVNWspcK-F1TbPav7C3C9NdeHDZMm_25fW9weix00,65
+rda_python_common-3.0.0.dist-info/top_level.txt,sha256=KVQmx7D3DD-jsiheqL8HdTrRE14hpRnZY5_ioMArA5k,18
+rda_python_common-3.0.0.dist-info/RECORD,,

rda_python_common-2.1.11.dist-info/RECORD

@@ -1,28 +0,0 @@
-rda_python_common/PgCMD.py,sha256=EYjG2Z4zEnvsXE1z-jt5UaNoEKxnOYYiMMzvW6HrKA4,20597
-rda_python_common/PgDBI.py,sha256=sOKQmzF_qmLR_vnj-NnFEYbLI05t2bVbhqlqy46iluA,76424
-rda_python_common/PgFile.py,sha256=7hyDFm40_NjQ_tg5WviMw_waYPdyXCi0DRCf0Av8eNE,99370
-rda_python_common/PgLOG.py,sha256=43YVpMjWEOLpaMUb4YTEYlDTvp7FTmDQ8V3TAKQrC4M,55228
-rda_python_common/PgLock.py,sha256=12i84nsGBuifSyPnm8IR63LvHvRuVU573D5QKFlHdOI,22623
-rda_python_common/PgOPT.py,sha256=Kn4JYezZhZwAn2usiIYHoHiymGHRgsN299dxyXbKwkI,56244
-rda_python_common/PgSIG.py,sha256=eTJJ3XxutsQ3JSg6uYRpH26ZmrVUup3ShqDFLWXLruA,35803
-rda_python_common/PgSplit.py,sha256=SSg5_Qu5PqP44EkqebO-V_cErNcdE2QtORgFHQ7RqlQ,8822
-rda_python_common/PgUtil.py,sha256=OqESKCd72b9g8m8jwjPJhXDtPYlW6G8oSOhwChvz2Cg,48600
-rda_python_common/__init__.py,sha256=58wQYxVa1MSXJMPsqe-4fnC1zvyZKe1UQVuc9Zqem6I,995
-rda_python_common/pg_cmd.py,sha256=PiQaAeb7l92LceqMwSzLpz9nD5pDRHJcEZxTDn-HeCs,33255
-rda_python_common/pg_dbi.py,sha256=q6LT4a4lwo-sM2LEqgrEVkAlh886xeKiz4feqRKw-7c,116238
-rda_python_common/pg_file.py,sha256=NgmF2pAl4955FZzMBIN_hQ8DjyUnxPputafrgamE47g,162230
-rda_python_common/pg_lock.py,sha256=31EaVDjCkcx3-n8-KnzG18R8Pz7Z6KyFsEqcml6Iq5c,32702
-rda_python_common/pg_log.py,sha256=n6Nh5g6cQbahAZv_Fe3xv2VGPJtLcCRw_kb6d8Rs9Fg,80806
-rda_python_common/pg_opt.py,sha256=sXrlzFWpR2XMak6NlA0MPvErBuQnY6gHM5OsHtoeIPQ,82496
-rda_python_common/pg_password.py,sha256=X-eIDwdqBhtrhrbDTNWle-0JtWsyIVZdDOZaBu7cFHM,2343
-rda_python_common/pg_sig.py,sha256=4wxE7NxeJyP8Q961uFPYrQCvlWm6D3Eu5RW9ipIr54s,53564
-rda_python_common/pg_split.py,sha256=aAWKUZPmZ-LQ_fJ3DSKzPKxJw0fMDJ2fgP8ZT629M30,16375
-rda_python_common/pg_util.py,sha256=bjp2civRIhqaBSR8oOtyRzYIZBdwB90SzmJLjRIA7fc,87280
-rda_python_common/pgpassword.py,sha256=aTQaO59QokWrv2EKom4TvKhNW2Mr6aFMMBVG4DCbcKI,5023
-rda_python_common/pgpassword.usg,sha256=Wrle6A8sdlMGx3ZEAmE6TNDPOlG84Whe0T3rCNFzPfY,2013
-rda_python_common-2.1.11.dist-info/licenses/LICENSE,sha256=1dck4EAQwv8QweDWCXDx-4Or0S8YwiCstaso_H57Pno,1097
-rda_python_common-2.1.11.dist-info/METADATA,sha256=i87yfkJjxDheTlHhevL8bnt6Jm9datVnG4vkMaSb6Nk,11093
-rda_python_common-2.1.11.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-rda_python_common-2.1.11.dist-info/entry_points.txt,sha256=pZgVNWspcK-F1TbPav7C3C9NdeHDZMm_25fW9weix00,65
-rda_python_common-2.1.11.dist-info/top_level.txt,sha256=KVQmx7D3DD-jsiheqL8HdTrRE14hpRnZY5_ioMArA5k,18
-rda_python_common-2.1.11.dist-info/RECORD,,