From bf21d2e3292fc3d736cf56654327a25e7782241e Mon Sep 17 00:00:00 2001
From: Tyler Goodlet <jgbt@protonmail.com>
Date: Wed, 31 May 2023 17:53:15 -0400
Subject: [PATCH] Rename default OHLCV `np.dtype` descriptions

Use `def_iohlcv_fields` for a name and instead of copying and inserting
the index field pop it for the non-index version. Drop creating
`np.dtype()` instances since `numpy`'s apis accept both input forms so
this is simpler on our end.
---
 piker/data/__init__.py   | 11 ++++-------
 piker/data/_sharedmem.py |  5 ++---
 piker/data/_source.py    | 34 +++++++++++++++++++++++++---------
 3 files changed, 31 insertions(+), 19 deletions(-)

diff --git a/piker/data/__init__.py b/piker/data/__init__.py
index 681bd3fe..cd0a1183 100644
--- a/piker/data/__init__.py
+++ b/piker/data/__init__.py
@@ -22,9 +22,6 @@ and storing data from your brokers as well as
 sharing live streams over a network.
 
 """
-from ._util import (
-    get_console_log,
-)
 from ._normalize import iterticks
 from ._sharedmem import (
     maybe_open_shm_array,
@@ -34,8 +31,8 @@ from ._sharedmem import (
     ShmArray,
 )
 from ._source import (
-    base_iohlc_dtype,
-    base_ohlc_dtype,
+    def_iohlcv_fields,
+    def_ohlcv_fields,
 )
 from .feed import (
     open_feed,
@@ -50,6 +47,6 @@ __all__ = [
     'attach_shm_array',
     'open_shm_array',
     'get_shm_token',
-    'base_iohlc_dtype',
-    'base_ohlc_dtype',
+    'def_iohlcv_fields',
+    'def_ohlcv_fields',
 ]
diff --git a/piker/data/_sharedmem.py b/piker/data/_sharedmem.py
index 2ed1c892..41dd0071 100644
--- a/piker/data/_sharedmem.py
+++ b/piker/data/_sharedmem.py
@@ -33,7 +33,7 @@ from numpy.lib import recfunctions as rfn
 import tractor
 
 from ._util import log
-from ._source import base_iohlc_dtype
+from ._source import def_iohlcv_fields
 from .types import Struct
 
 
@@ -168,7 +168,7 @@ def _make_token(
     to access a shared array.
 
     '''
-    dtype = base_iohlc_dtype if dtype is None else dtype
+    dtype = def_iohlcv_fields if dtype is None else dtype
     return _Token(
         shm_name=key,
         shm_first_index_name=key + "_first",
@@ -258,7 +258,6 @@ class ShmArray:
         # to load an empty array..
         if len(a) == 0 and self._post_init:
             raise RuntimeError('Empty array race condition hit!?')
-            # breakpoint()
 
         return a
 
diff --git a/piker/data/_source.py b/piker/data/_source.py
index d1d8be02..7f739d7d 100644
--- a/piker/data/_source.py
+++ b/piker/data/_source.py
@@ -23,26 +23,42 @@ from bidict import bidict
 import numpy as np
 
 
-ohlc_fields = [
-    ('time', float),
+def_iohlcv_fields: list[tuple[str, type]] = [
+
+    # YES WE KNOW, this isn't needed in polars but we use it for doing
+    # ring-buffer like pre/append ops our our `ShmArray` real-time
+    # numpy-array buffering system such that there is a master index
+    # that can be used for index-arithmetic when write data to the
+    # "middle" of the array. See the ``tractor.ipc.shm`` pkg for more
+    # details.
+    ('index', int),
+
+    # presume int for epoch stamps since it's most common
+    # and makes the most sense to avoid float rounding issues.
+    # TODO: if we want higher reso we should use the new
+    # ``time.time_ns()`` in python 3.10+
+    ('time', int),
     ('open', float),
     ('high', float),
     ('low', float),
     ('close', float),
     ('volume', float),
-    ('bar_wap', float),
+
+    # TODO: can we elim this from default field set to save on mem?
+    # i think only kraken really uses this in terms of what we get from
+    # their ohlc history API?
+    ('bar_wap', float),  # shouldn't be default right?
 ]
 
-ohlc_with_index = ohlc_fields.copy()
-ohlc_with_index.insert(0, ('index', int))
-
-# our minimum structured array layout for ohlc data
-base_iohlc_dtype = np.dtype(ohlc_with_index)
-base_ohlc_dtype = np.dtype(ohlc_fields)
+# remove index field
+def_ohlcv_fields: list[tuple[str, type]] = def_iohlcv_fields.copy()
+def_ohlcv_fields.pop(0)
+assert (len(def_iohlcv_fields) - len(def_ohlcv_fields)) == 1
 
 # TODO: for now need to construct this manually for readonly arrays, see
 # https://github.com/numba/numba/issues/4511
 # from numba import from_dtype
+# base_ohlc_dtype = np.dtype(def_ohlc_fields)
 # numba_ohlc_dtype = from_dtype(base_ohlc_dtype)
 
 # map time frame "keys" to seconds values