diff --git a/.flake8 b/.flake8 index b63059e..0034415 100644 --- a/.flake8 +++ b/.flake8 @@ -1,3 +1,3 @@ [flake8] -max-line-length = 88 +max-line-length = 140 extend-ignore = E203, E402 \ No newline at end of file diff --git a/.pylintrc b/.pylintrc index 8437189..e218f95 100644 --- a/.pylintrc +++ b/.pylintrc @@ -1,639 +1,339 @@ -[MAIN] +[MASTER] -# Analyse import fallback blocks. This can be used to support both Python 2 and -# 3 compatible code, which means that the block might have code that exists -# only in one or another interpreter, leading to false positives when analysed. -analyse-fallback-blocks=no - -# Clear in-memory caches upon conclusion of linting. Useful if running pylint -# in a server-like mode. -clear-cache-post-run=no - -# Load and enable all available extensions. Use --list-extensions to see a list -# all available extensions. -#enable-all-extensions= - -# In error mode, messages with a category besides ERROR or FATAL are -# suppressed, and no reports are done by default. Error mode is compatible with -# disabling specific errors. -#errors-only= - -# Always return a 0 (non-error) status code, even if lint errors are found. -# This is primarily useful in continuous integration scripts. -#exit-zero= - -# A comma-separated list of package or module names from where C extensions may -# be loaded. Extensions are loading into the active Python interpreter and may -# run arbitrary code. -extension-pkg-allow-list= - -# A comma-separated list of package or module names from where C extensions may -# be loaded. Extensions are loading into the active Python interpreter and may -# run arbitrary code. (This is an alternative name to extension-pkg-allow-list -# for backward compatibility.) -extension-pkg-whitelist= - -# Return non-zero exit code if any of these messages/categories are detected, -# even if score is above --fail-under value. Syntax same as enable. Messages -# specified are enabled, while categories only check already-enabled messages. -fail-on= - -# Specify a score threshold under which the program will exit with error. -fail-under=10 - -# Interpret the stdin as a python script, whose filename needs to be passed as -# the module_or_package argument. -#from-stdin= - -# Files or directories to be skipped. They should be base names, not paths. -ignore=CVS - -# Add files or directories matching the regular expressions patterns to the -# ignore-list. The regex matches against paths and can be in Posix or Windows -# format. Because '\\' represents the directory delimiter on Windows systems, -# it can't be used as an escape character. -ignore-paths= - -# Files or directories matching the regular expression patterns are skipped. -# The regex matches against base names, not paths. The default value ignores -# Emacs file locks -ignore-patterns=^\.# - -# List of module names for which member attributes should not be checked -# (useful for modules/projects where namespaces are manipulated during runtime -# and thus existing member attributes cannot be deduced by static analysis). It -# supports qualified module names, as well as Unix pattern matching. -ignored-modules= +# Specify a configuration file. +#rcfile= # Python code to execute, usually for sys.path manipulation such as # pygtk.require(). #init-hook= -# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the -# number of processors available to use, and will cap the count on Windows to -# avoid hangs. -jobs=1 - -# Control the amount of potential inferred values when inferring a single -# object. This can help the performance when dealing with large functions or -# complex, nested conditions. -limit-inference-results=100 - -# List of plugins (as comma separated values of python module names) to load, -# usually to register additional checkers. -load-plugins= +# Add files or directories to the blacklist. They should be base names, not +# paths. +ignore=CVS # Pickle collected data for later comparisons. persistent=yes -# Minimum Python version to use for version dependent checks. Will default to -# the version used to run pylint. -py-version=3.10 - -# Discover python modules and packages in the file system subtree. -recursive=no - -# Add paths to the list of the source roots. Supports globbing patterns. The -# source root is an absolute path or a path relative to the current working -# directory used to determine a package namespace for modules located under the -# source root. -source-roots= +# List of plugins (as comma separated values of python modules names) to load, +# usually to register additional checkers. +load-plugins= -# When enabled, pylint would attempt to guess common misconfiguration and emit -# user-friendly hints instead of false-positive error messages. -suggestion-mode=yes +# Use multiple processes to speed up Pylint. +jobs=1 # Allow loading of arbitrary C extensions. Extensions are imported into the # active Python interpreter and may run arbitrary code. unsafe-load-any-extension=no -# In verbose mode, extra non-checker-related info will be displayed. -#verbose= - - -[BASIC] - -# Naming style matching correct argument names. -argument-naming-style=snake_case - -# Regular expression matching correct argument names. Overrides argument- -# naming-style. If left empty, argument names will be checked with the set -# naming style. -#argument-rgx= - -# Naming style matching correct attribute names. -attr-naming-style=snake_case - -# Regular expression matching correct attribute names. Overrides attr-naming- -# style. If left empty, attribute names will be checked with the set naming -# style. -#attr-rgx= - -# Bad variable names which should always be refused, separated by a comma. -bad-names=foo, - bar, - baz, - toto, - tutu, - tata - -# Bad variable names regexes, separated by a comma. If names match any regex, -# they will always be refused -bad-names-rgxs= - -# Naming style matching correct class attribute names. -class-attribute-naming-style=any - -# Regular expression matching correct class attribute names. Overrides class- -# attribute-naming-style. If left empty, class attribute names will be checked -# with the set naming style. -#class-attribute-rgx= - -# Naming style matching correct class constant names. -class-const-naming-style=UPPER_CASE - -# Regular expression matching correct class constant names. Overrides class- -# const-naming-style. If left empty, class constant names will be checked with -# the set naming style. -#class-const-rgx= - -# Naming style matching correct class names. -class-naming-style=PascalCase - -# Regular expression matching correct class names. Overrides class-naming- -# style. If left empty, class names will be checked with the set naming style. -#class-rgx= - -# Naming style matching correct constant names. -const-naming-style=UPPER_CASE - -# Regular expression matching correct constant names. Overrides const-naming- -# style. If left empty, constant names will be checked with the set naming -# style. -#const-rgx= - -# Minimum line length for functions/classes that require docstrings, shorter -# ones are exempt. -docstring-min-length=-1 - -# Naming style matching correct function names. -function-naming-style=snake_case - -# Regular expression matching correct function names. Overrides function- -# naming-style. If left empty, function names will be checked with the set -# naming style. -#function-rgx= - -# Good variable names which should always be accepted, separated by a comma. -good-names=i, - j, - k, - ex, - Run, - _ - -# Good variable names regexes, separated by a comma. If names match any regex, -# they will always be accepted -good-names-rgxs= - -# Include a hint for the correct naming format with invalid-name. -include-naming-hint=no - -# Naming style matching correct inline iteration names. -inlinevar-naming-style=any - -# Regular expression matching correct inline iteration names. Overrides -# inlinevar-naming-style. If left empty, inline iteration names will be checked -# with the set naming style. -#inlinevar-rgx= - -# Naming style matching correct method names. -method-naming-style=snake_case - -# Regular expression matching correct method names. Overrides method-naming- -# style. If left empty, method names will be checked with the set naming style. -#method-rgx= - -# Naming style matching correct module names. -module-naming-style=snake_case - -# Regular expression matching correct module names. Overrides module-naming- -# style. If left empty, module names will be checked with the set naming style. -#module-rgx= - -# Colon-delimited sets of names that determine each other's naming style when -# the name regexes allow several styles. -name-group= - -# Regular expression which should only match function or class names that do -# not require a docstring. -no-docstring-rgx=^_ +# A comma-separated list of package or module names from where C extensions may +# be loaded. Extensions are loading into the active Python interpreter and may +# run arbitrary code +extension-pkg-whitelist= -# List of decorators that produce properties, such as abc.abstractproperty. Add -# to this list to register other decorators that produce valid properties. -# These decorators are taken in consideration only for invalid-name. -property-classes=abc.abstractproperty -# Regular expression matching correct type alias names. If left empty, type -# alias names will be checked with the set naming style. -#typealias-rgx= +[MESSAGES CONTROL] -# Regular expression matching correct type variable names. If left empty, type -# variable names will be checked with the set naming style. -#typevar-rgx= +# Only show warnings with the listed confidence levels. Leave empty to show +# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED +confidence= -# Naming style matching correct variable names. -variable-naming-style=snake_case +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once).You can also use "--disable=all" to +# disable everything first and then reenable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use"--disable=all --enable=classes +# --disable=W" + +disable= + attribute-defined-outside-init, + duplicate-code, + invalid-name, + missing-docstring, + protected-access, + too-few-public-methods, + no-member, + # handled by black + format, + ungrouped-imports, + too-many-instance-attributes, + no-method-argument, + broad-except, + # remove this once we refactor context class + too-many-public-methods, + # due to pylint bug with module called parser + deprecated-module, + import-error -# Regular expression matching correct variable names. Overrides variable- -# naming-style. If left empty, variable names will be checked with the set -# naming style. -#variable-rgx= +[REPORTS] -[CLASSES] +# Set the output format. Available formats are text, parseable, colorized, msvs +# (visual studio) and html. You can also give a reporter class, eg +# mypackage.mymodule.MyReporterClass. +output-format=text -# Warn about protected attribute access inside special methods -check-protected-access-in-special-methods=no -# List of method names used to declare (i.e. assign) instance attributes. -defining-attr-methods=__init__, - __new__, - setUp, - asyncSetUp, - __post_init__ +# Tells whether to display a full report or only the messages +reports=no -# List of member names, which should be excluded from the protected access -# warning. -exclude-protected=_asdict,_fields,_replace,_source,_make,os._exit +# Python expression which should return a note less than 10 (10 is the highest +# note). You have access to the variables errors warning, statement which +# respectively contain the number of errors / warnings messages and the total +# number of statements analyzed. This is used by the global evaluation report +# (RP0004). +evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10) -# List of valid names for the first argument in a class method. -valid-classmethod-first-arg=cls +# Template used to display messages. This is a python new-style format string +# used to format the message information. See doc for all details +#msg-template= -# List of valid names for the first argument in a metaclass class method. -valid-metaclass-classmethod-first-arg=mcs +[LOGGING] -[DESIGN] +# Logging modules to check that the string format arguments are in logging +# function parameter format +logging-modules=logging -# List of regular expressions of class ancestor names to ignore when counting -# public methods (see R0903) -exclude-too-few-public-methods= -# List of qualified class names to ignore when counting class parents (see -# R0901) -ignored-parents= +[MISCELLANEOUS] -# Maximum number of arguments for function / method. -max-args=5 +# List of note tags to take in consideration, separated by a comma. +notes=FIXME,XXX,TODO -# Maximum number of attributes for a class (see R0902). -max-attributes=7 -# Maximum number of boolean expressions in an if statement (see R0916). -max-bool-expr=5 +[SIMILARITIES] -# Maximum number of branch for function / method body. -max-branches=12 +# Minimum lines number of a similarity. +min-similarity-lines=4 -# Maximum number of locals for function / method body. -max-locals=15 +# Ignore comments when computing similarities. +ignore-comments=yes -# Maximum number of parents for a class (see R0901). -max-parents=7 +# Ignore docstrings when computing similarities. +ignore-docstrings=yes -# Maximum number of public methods for a class (see R0904). -max-public-methods=20 +# Ignore imports when computing similarities. +ignore-imports=no -# Maximum number of return / yield for function / method body. -max-returns=6 -# Maximum number of statements in function / method body. -max-statements=50 +[VARIABLES] -# Minimum number of public methods for a class (see R0903). -min-public-methods=2 +# Tells whether we should check for unused import in __init__ files. +init-import=no +# A regular expression matching the name of dummy variables (i.e. expectedly +# not used). +dummy-variables-rgx=_$|dummy -[EXCEPTIONS] +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid defining new builtins when possible. +additional-builtins= -# Exceptions that will emit a warning when caught. -overgeneral-exceptions=builtins.BaseException,builtins.Exception +# List of strings which can identify a callback function by name. A callback +# name must start or end with one of those strings. +callbacks=cb_,_cb [FORMAT] -# Expected format of line ending, e.g. empty (any line ending), LF or CRLF. -expected-line-ending-format= +# Maximum number of characters on a single line. +max-line-length=140 # Regexp for a line that is allowed to be longer than the limit. ignore-long-lines=^\s*(# )??$ -# Number of spaces of indent required inside a hanging or continued line. -indent-after-paren=4 - -# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 -# tab). -indent-string=' ' - -# Maximum number of characters on a single line. -max-line-length=88 - -# Maximum number of lines in a module. -max-module-lines=1000 - -# Allow the body of a class to be on the same line as the declaration if body -# contains single statement. -single-line-class-stmt=no - # Allow the body of an if to be on the same line as the test if there is no # else. single-line-if-stmt=no +# Maximum number of lines in a module +max-module-lines=2000 -[IMPORTS] - -# List of modules that can be imported at any level, not just the top level -# one. -allow-any-import-level= - -# Allow explicit reexports by alias from a package __init__. -allow-reexport-from-package=no - -# Allow wildcard imports from modules that define __all__. -allow-wildcard-with-all=no - -# Deprecated modules which should not be used, separated by a comma. -deprecated-modules= - -# Output a graph (.gv or any supported image format) of external dependencies -# to the given file (report RP0402 must not be disabled). -ext-import-graph= - -# Output a graph (.gv or any supported image format) of all (i.e. internal and -# external) dependencies to the given file (report RP0402 must not be -# disabled). -import-graph= - -# Output a graph (.gv or any supported image format) of internal dependencies -# to the given file (report RP0402 must not be disabled). -int-import-graph= - -# Force import order to recognize a module as part of the standard -# compatibility libraries. -known-standard-library= - -# Force import order to recognize a module as part of a third party library. -known-third-party=enchant - -# Couples of modules and preferred modules, separated by a comma. -preferred-modules= +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' +# Number of spaces of indent required inside a hanging or continued line. +indent-after-paren=4 -[LOGGING] +# Expected format of line ending, e.g. empty (any line ending), LF or CRLF. +expected-line-ending-format= -# The type of string formatting that logging methods do. `old` means using % -# formatting, `new` is for `{}` formatting. -logging-format-style=old -# Logging modules to check that the string format arguments are in logging -# function parameter format. -logging-modules=logging +[BASIC] +# Good variable names which should always be accepted, separated by a comma +good-names=i,j,k,ex,Run,_ -[MESSAGES CONTROL] +# Bad variable names which should always be refused, separated by a comma +bad-names=foo,bar,baz,toto,tutu,tata -# Only show warnings with the listed confidence levels. Leave empty to show -# all. Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE, -# UNDEFINED. -confidence=HIGH, - CONTROL_FLOW, - INFERENCE, - INFERENCE_FAILURE, - UNDEFINED +# Colon-delimited sets of names that determine each other's naming style when +# the name regexes allow several styles. +name-group= -# Disable the message, report, category or checker with the given id(s). You -# can either give multiple identifiers separated by comma (,) or put this -# option multiple times (only on the command line, not in the configuration -# file where it should appear only once). You can also use "--disable=all" to -# disable everything first and then re-enable specific checks. For example, if -# you want to run only the similarities checker, you can use "--disable=all -# --enable=similarities". If you want to run only the classes checker, but have -# no Warning level messages displayed, use "--disable=all --enable=classes -# --disable=W". -disable=raw-checker-failed, - bad-inline-option, - locally-disabled, - file-ignored, - suppressed-message, - useless-suppression, - missing-docstring, - broad-except, - # handled by black - format, - deprecated-pragma, - too-many-locals, - use-implicit-booleaness-not-comparison-to-string, - use-implicit-booleaness-not-comparison-to-zero, - use-symbolic-message-instead - -# Enable the message, report, category or checker with the given id(s). You can -# either give multiple identifier separated by comma (,) or put this option -# multiple time (only on the command line, not in the configuration file where -# it should appear only once). See also the "--disable" option for examples. -enable= - - -[METHOD_ARGS] - -# List of qualified names (i.e., library.method) which require a timeout -# parameter e.g. 'requests.api.get,requests.api.post' -timeout-methods=requests.api.delete,requests.api.get,requests.api.head,requests.api.options,requests.api.patch,requests.api.post,requests.api.put,requests.api.request +# Include a hint for the correct naming format with invalid-name +include-naming-hint=no +# Regular expression matching correct function names +function-rgx=[a-z_][a-z0-9_]{2,30}$ -[MISCELLANEOUS] +# Regular expression matching correct variable names +variable-rgx=[a-z_][a-z0-9_]{2,30}$ -# List of note tags to take in consideration, separated by a comma. -notes=FIXME, - XXX, - TODO +# Regular expression matching correct constant names +const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__))$ -# Regular expression of note tags to take in consideration. -notes-rgx= +# Regular expression matching correct attribute names +attr-rgx=[a-z_][a-z0-9_]{2,}$ +# Regular expression matching correct argument names +argument-rgx=[a-z_][a-z0-9_]{2,30}$ -[REFACTORING] -# Maximum number of nested blocks for function / method body -max-nested-blocks=5 +# Regular expression matching correct class attribute names +class-attribute-rgx=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$ -# Complete name of functions that never returns. When checking for -# inconsistent-return-statements if a never returning function is called then -# it will be considered as an explicit return statement and no message will be -# printed. -never-returning-functions=sys.exit,argparse.parse_error +# Regular expression matching correct inline iteration names +inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$ +# Regular expression matching correct class names +class-rgx=[A-Z_][a-zA-Z0-9]+$ -[REPORTS] +# Regular expression matching correct module names +module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$ -# Python expression which should return a score less than or equal to 10. You -# have access to the variables 'fatal', 'error', 'warning', 'refactor', -# 'convention', and 'info' which contain the number of messages in each -# category, as well as 'statement' which is the total number of statements -# analyzed. This score is used by the global evaluation report (RP0004). -evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)) +# Regular expression matching correct method names +method-rgx=[a-z_][a-z0-9_]{2,}$ -# Template used to display messages. This is a python new-style format string -# used to format the message information. See doc for all details. -msg-template= - -# Set the output format. Available formats are: text, parseable, colorized, -# json2 (improved json format), json (old json format) and msvs (visual -# studio). You can also give a reporter class, e.g. -# mypackage.mymodule.MyReporterClass. -#output-format= +# Regular expression which should only match function or class names that do +# not require a docstring. +no-docstring-rgx=__.*__ -# Tells whether to display a full report or only the messages. -reports=no +# Minimum line length for functions/classes that require docstrings, shorter +# ones are exempt. +docstring-min-length=-1 -# Activate the evaluation score. -score=yes +# List of decorators that define properties, such as abc.abstractproperty. +property-classes=abc.abstractproperty -[SIMILARITIES] +[TYPECHECK] -# Comments are removed from the similarity computation -ignore-comments=yes +# Tells whether missing members accessed in mixin class should be ignored. A +# mixin class is detected if its name ends with "mixin" (case insensitive). +ignore-mixin-members=yes -# Docstrings are removed from the similarity computation -ignore-docstrings=yes +# List of module names for which member attributes should not be checked +# (useful for modules/projects where namespaces are manipulated during runtime +# and thus existing member attributes cannot be deduced by static analysis +ignored-modules= -# Imports are removed from the similarity computation -ignore-imports=yes +# List of classes names for which member attributes should not be checked +# (useful for classes with attributes dynamically set). +ignored-classes=SQLObject, optparse.Values, thread._local, _thread._local -# Signatures are removed from the similarity computation -ignore-signatures=yes +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E1101 when accessed. Python regular +# expressions are accepted. +generated-members=REQUEST,acl_users,aq_parent -# Minimum lines number of a similarity. -min-similarity-lines=4 +# List of decorators that create context managers from functions, such as +# contextlib.contextmanager. +contextmanager-decorators=contextlib.contextmanager [SPELLING] -# Limits count of emitted suggestions for spelling mistakes. -max-spelling-suggestions=4 - -# Spelling dictionary name. No available dictionaries : You need to install -# both the python package and the system dependency for enchant to work. +# Spelling dictionary name. Available dictionaries: none. To make it working +# install python-enchant package. spelling-dict= -# List of comma separated words that should be considered directives if they -# appear at the beginning of a comment and should not be checked. -spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy: - # List of comma separated words that should not be checked. spelling-ignore-words= -# A path to a file that contains the private dictionary; one word per line. +# A path to a file that contains private dictionary; one word per line. spelling-private-dict-file= -# Tells whether to store unknown words to the private dictionary (see the -# --spelling-private-dict-file option) instead of raising a message. +# Tells whether to store unknown words to indicated private dictionary in +# --spelling-private-dict-file option instead of raising a message. spelling-store-unknown-words=no -[STRING] +[DESIGN] -# This flag controls whether inconsistent-quotes generates a warning when the -# character used as a quote delimiter is used inconsistently within a module. -check-quote-consistency=no +# Maximum number of arguments for function / method +max-args=10 -# This flag controls whether the implicit-str-concat should generate a warning -# on implicit string concatenation in sequences defined over several lines. -check-str-concat-over-line-jumps=no +# Argument names that match this expression will be ignored. Default to name +# with leading underscore +ignored-argument-names=_.* +# Maximum number of locals for function / method body +max-locals=25 -[TYPECHECK] +# Maximum number of return / yield for function / method body +max-returns=11 -# List of decorators that produce context managers, such as -# contextlib.contextmanager. Add to this list to register other decorators that -# produce valid context managers. -contextmanager-decorators=contextlib.contextmanager +# Maximum number of branch for function / method body +max-branches=26 -# List of members which are set dynamically and missed by pylint inference -# system, and so shouldn't trigger E1101 when accessed. Python regular -# expressions are accepted. -generated-members= +# Maximum number of statements in function / method body +max-statements=100 -# Tells whether to warn about missing members when the owner of the attribute -# is inferred to be None. -ignore-none=yes +# Maximum number of parents for a class (see R0901). +max-parents=7 -# This flag controls whether pylint should warn about no-member and similar -# checks whenever an opaque object is returned when inferring. The inference -# can return multiple potential results while evaluating a Python object, but -# some branches might not be evaluated, which results in partial inference. In -# that case, it might be useful to still emit no-member and other checks for -# the rest of the inferred objects. -ignore-on-opaque-inference=yes +# Maximum number of attributes for a class (see R0902). +max-attributes=11 -# List of symbolic message names to ignore for Mixin members. -ignored-checks-for-mixins=no-member, - not-async-context-manager, - not-context-manager, - attribute-defined-outside-init +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 -# List of class names for which member attributes should not be checked (useful -# for classes with dynamically set attributes). This supports the use of -# qualified names. -ignored-classes=optparse.Values,thread._local,_thread._local,argparse.Namespace +# Maximum number of public methods for a class (see R0904). +max-public-methods=25 -# Show a hint with possible names when a member name was not found. The aspect -# of finding the hint is based on edit distance. -missing-member-hint=yes -# The minimum edit distance a name should have in order to be considered a -# similar match for a missing member name. -missing-member-hint-distance=1 +[CLASSES] -# The total number of similar names that should be taken in consideration when -# showing a hint for a missing member. -missing-member-max-choices=1 +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__,__new__,setUp,__post_init__ -# Regex pattern to define which classes are considered mixins. -mixin-class-rgx=.*[Mm]ixin +# List of valid names for the first argument in a class method. +valid-classmethod-first-arg=cls -# List of decorators that change the signature of a decorated function. -signature-mutators= +# List of valid names for the first argument in a metaclass class method. +valid-metaclass-classmethod-first-arg=mcs +# List of member names, which should be excluded from the protected access +# warning. +exclude-protected=_asdict,_fields,_replace,_source,_make -[VARIABLES] -# List of additional names supposed to be defined in builtins. Remember that -# you should avoid defining new builtins when possible. -additional-builtins= +[IMPORTS] -# Tells whether unused global variables should be treated as a violation. -allow-global-unused-variables=yes +# Deprecated modules which should not be used, separated by a comma +deprecated-modules=regsub,TERMIOS,Bastion,rexec -# List of names allowed to shadow builtins -allowed-redefined-builtins= +# Create a graph of every (i.e. internal and external) dependencies in the +# given file (report RP0402 must not be disabled) +import-graph= -# List of strings which can identify a callback function by name. A callback -# name must start or end with one of those strings. -callbacks=cb_, - _cb +# Create a graph of external dependencies in the given file (report RP0402 must +# not be disabled) +ext-import-graph= -# A regular expression matching the name of dummy variables (i.e. expected to -# not be used). -dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_ +# Create a graph of internal dependencies in the given file (report RP0402 must +# not be disabled) +int-import-graph= -# Argument names that match this expression will be ignored. -ignored-argument-names=_.*|^ignored_|^unused_ -# Tells whether we should check for unused import in __init__ files. -init-import=no +[EXCEPTIONS] -# List of qualified module names which can have objects that can redefine -# builtins. -redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io +# Exceptions that will emit a warning when being caught. Defaults to +# "Exception" +overgeneral-exceptions=builtins.BaseException, + builtins.Exception diff --git a/Makefile b/Makefile index 9982616..c8e3a67 100644 --- a/Makefile +++ b/Makefile @@ -21,8 +21,6 @@ install: lint: pipenv run flake8 notebooks pipenv run pylint --rcfile=.pylintrc notebooks - pipenv run nbqa flake8 notebooks - pipenv run nbqa pylint --rcfile=.pylintrc notebooks format: pipenv run black notebooks diff --git a/Pipfile b/Pipfile index e5d754d..cb94b70 100644 --- a/Pipfile +++ b/Pipfile @@ -20,8 +20,8 @@ tenacity = "==8.2.3" pandas = "==2.2.0" seaborn = "==0.11.2" plotly = "==5.18.0" -jupyterlab = "== 4.1.2" - +jupyterlab = "==4.1.2" +appnope = "==0.1.4" [requires] python_version = "3.10" diff --git a/Pipfile.lock b/Pipfile.lock index 5ff6b17..a5ef62a 100644 --- a/Pipfile.lock +++ b/Pipfile.lock @@ -1,7 +1,7 @@ { "_meta": { "hash": { - "sha256": "5b232d8fe8b2085ad38741a513420f90cb98d90635e4647fbce0efef2105e22c" + "sha256": "68c7a22cfdaa662cb2308be9895630f1767b632e4b8a27f81f08e699e2c563c9" }, "pipfile-spec": 6, "requires": { @@ -114,6 +114,15 @@ "markers": "python_version >= '3.8'", "version": "==4.3.0" }, + "appnope": { + "hashes": [ + "sha256:1de3860566df9caf38f01f86f65e0e13e379af54f9e4bee1e66b48f2efffd1ee", + "sha256:502575ee11cd7a28c0205f379b525beefebab9d161b7c964670864014ed7213c" + ], + "index": "pypi", + "markers": "python_version >= '3.6'", + "version": "==0.1.4" + }, "argon2-cffi": { "hashes": [ "sha256:879c3e79a2729ce768ebb7d36d4609e3a78a4ca2ec3a9f12286ca057e3d0db08", @@ -655,19 +664,19 @@ }, "httpcore": { "hashes": [ - "sha256:5c0f9546ad17dac4d0772b0808856eb616eb8b48ce94f49ed819fd6982a8a544", - "sha256:9a6a501c3099307d9fd76ac244e08503427679b1e81ceb1d922485e2f2462ad2" + "sha256:ac418c1db41bade2ad53ae2f3834a3a0f5ae76b56cf5aa497d2d033384fc7d73", + "sha256:cb2839ccfcba0d2d3c1131d3c3e26dfc327326fbe7a5dc0dbfe9f6c9151bb022" ], "markers": "python_version >= '3.8'", - "version": "==1.0.3" + "version": "==1.0.4" }, "httpx": { "hashes": [ - "sha256:451b55c30d5185ea6b23c2c793abf9bb237d2a7dfb901ced6ff69ad37ec1dfaf", - "sha256:8915f5a3627c4d47b73e8202457cb28f1266982d1159bd5779d86a80c0eab1cd" + "sha256:71d5465162c13681bff01ad59b2cc68dd838ea1f10e51574bac27103f00c91a5", + "sha256:a0cb88a46f32dc874e04ee956e4c2764aba2aa228f650b06788ba6bda2962ab5" ], "markers": "python_version >= '3.8'", - "version": "==0.26.0" + "version": "==0.27.0" }, "idna": { "hashes": [ @@ -687,11 +696,11 @@ }, "ipython": { "hashes": [ - "sha256:1050a3ab8473488d7eee163796b02e511d0735cf43a04ba2a8348bd0f2eaf8a5", - "sha256:48fbc236fbe0e138b88773fa0437751f14c3645fb483f1d4c5dee58b37e5ce73" + "sha256:39c6f9efc079fb19bfb0f17eee903978fe9a290b1b82d68196c641cecb76ea22", + "sha256:869335e8cded62ffb6fac8928e5287a05433d6462e3ebaac25f4216474dd6bc4" ], "markers": "python_version >= '3.10'", - "version": "==8.21.0" + "version": "==8.22.1" }, "isoduration": { "hashes": [ @@ -1309,7 +1318,7 @@ "sha256:7236d1e080e4936be2dc3e326cec0af72acf9212a7e1d060210e70a47e253523", "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f" ], - "markers": "sys_platform != 'win32'", + "markers": "sys_platform != 'win32' and sys_platform != 'emscripten'", "version": "==4.9.0" }, "pillow": { @@ -2313,11 +2322,11 @@ }, "ipython": { "hashes": [ - "sha256:1050a3ab8473488d7eee163796b02e511d0735cf43a04ba2a8348bd0f2eaf8a5", - "sha256:48fbc236fbe0e138b88773fa0437751f14c3645fb483f1d4c5dee58b37e5ce73" + "sha256:39c6f9efc079fb19bfb0f17eee903978fe9a290b1b82d68196c641cecb76ea22", + "sha256:869335e8cded62ffb6fac8928e5287a05433d6462e3ebaac25f4216474dd6bc4" ], "markers": "python_version >= '3.10'", - "version": "==8.21.0" + "version": "==8.22.1" }, "isort": { "hashes": [ @@ -2398,7 +2407,7 @@ "sha256:7236d1e080e4936be2dc3e326cec0af72acf9212a7e1d060210e70a47e253523", "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f" ], - "markers": "sys_platform != 'win32'", + "markers": "sys_platform != 'win32' and sys_platform != 'emscripten'", "version": "==4.9.0" }, "platformdirs": { diff --git a/notebooks/analytics/__init__.py b/notebooks/analytics/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/notebooks/analytics/session_content.ipynb b/notebooks/analytics/session_content.ipynb new file mode 100644 index 0000000..a3c90ba --- /dev/null +++ b/notebooks/analytics/session_content.ipynb @@ -0,0 +1,169 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "23c538dc-a51f-474d-b448-10df539e1c08", + "metadata": {}, + "source": [ + "# This Notebook uses the Analytics API to get the content for a specified Session\n", + "\n", + "## Before you Begin\n", + "Make sure you have access to your Moveo Analytics API Key and Account ID\n", + "\n", + "## More Information\n", + "For more information about the Analytics API, please visit: \n", + "* https://docs.moveo.ai/docs/analytics/api_overview\n", + "* https://docs.moveo.ai/docs/analytics/log_sessions_content" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "07acb732-7309-4825-b226-cf9e7bcdf42a", + "metadata": {}, + "outputs": [], + "source": [ + "from utils.common import execute_query, initialize_graphql_clinet" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5e54ef33-8e2e-4734-a9d6-e27da90d2a82", + "metadata": {}, + "outputs": [], + "source": [ + "# substitute your Analytics API Key\n", + "GRAPHQL_API_KEY = \"\"\n", + "# substitute your Account ID. You can find the account ID,\n", + "# by going to the settings of your account, then click on \"information\".\n", + "ACCOUNT_ID = \"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "40181c4d-8511-4070-9731-d1b63bd0bd25", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "973c7a16-32d8-416e-9ac5-211d31775faf", + "metadata": {}, + "outputs": [], + "source": [ + "client = initialize_graphql_clinet(ACCOUNT_ID, GRAPHQL_API_KEY)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "717830c1-02e7-4fa2-b92a-a231c0e046cc", + "metadata": {}, + "outputs": [], + "source": [ + "# more information: https://docs.moveo.ai/docs/analytics/log_sessions_content\n", + "query = \"\"\"\n", + " query SessionContentV2($sessionId: String) {\n", + " rows: log_session_content_v2(args: { session_id: $sessionId }) {\n", + " messages\n", + " brain_id\n", + " brain_parent_id\n", + " avg_confidence\n", + " brain_version\n", + " channel\n", + " channel_user_id\n", + " desk_id\n", + " end_time\n", + " external_user_id\n", + " integration_id\n", + " is_contained\n", + " is_covered\n", + " is_test\n", + " min_confidence\n", + " participated_agents\n", + " rating\n", + " session_id\n", + " start_time\n", + " tags\n", + " total_user_messages\n", + " user_id\n", + " user_name\n", + " }\n", + " }\n", + " \"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9eecb71c-1f4c-48ae-abdf-705d01a168cc", + "metadata": {}, + "outputs": [], + "source": [ + "# Moveo session_id that uniquely identifies a conversation\n", + "session_id = \"\"\n", + "# execute_query receives as arguments the GraphQL client, query and corresponding variables (dictionary)\n", + "session_content = execute_query(client, query, {\"sessionId\": session_id})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "69629723-1b4f-4f40-8372-59ba47c27c1c", + "metadata": {}, + "outputs": [], + "source": [ + "# extract the document ids found in the session\n", + "docs_found = set()\n", + "for message in session_content[0][\"messages\"]:\n", + " sources = message.get(\"collection_sources\") or []\n", + " docs_found = docs_found.union(\n", + " set([source[\"document_id\"] for source in sources if \"document_id\" in source])\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "096fbdb4-941a-4933-966c-080560ac59ea", + "metadata": {}, + "outputs": [], + "source": [ + "print(docs_found)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8b404298-e2bb-4f0f-9aa1-0bbc24dd7caf", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.12" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/analytics/session_duration.ipynb b/notebooks/analytics/session_duration.ipynb new file mode 100644 index 0000000..dfd1c5d --- /dev/null +++ b/notebooks/analytics/session_duration.ipynb @@ -0,0 +1,232 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "23c538dc-a51f-474d-b448-10df539e1c08", + "metadata": {}, + "source": [ + "# This Notebook uses the Analytics API to get the average duration of all, (non) contained and (non) covered Brain sessions.\n", + "\n", + "## Before you Begin\n", + "Make sure you have access to your Moveo Analytics API Key and Account ID\n", + "\n", + "## More Information\n", + "For more information about the Analytics API, please visit: \n", + "* https://docs.moveo.ai/docs/analytics/api_overview\n", + "* https://docs.moveo.ai/docs/analytics/brain_session_duration" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "07acb732-7309-4825-b226-cf9e7bcdf42a", + "metadata": {}, + "outputs": [], + "source": [ + "from utils.common import (\n", + " execute_query,\n", + " initialize_graphql_clinet,\n", + " serialize_list_variable,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5e54ef33-8e2e-4734-a9d6-e27da90d2a82", + "metadata": {}, + "outputs": [], + "source": [ + "# substitute your Analytics API Key\n", + "GRAPHQL_API_KEY = \"\"\n", + "# substitute your Account ID. You can find the account ID, by going to the settings of your account, then click on \"information\".\n", + "ACCOUNT_ID = \"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "40181c4d-8511-4070-9731-d1b63bd0bd25", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "973c7a16-32d8-416e-9ac5-211d31775faf", + "metadata": {}, + "outputs": [], + "source": [ + "client = initialize_graphql_clinet(ACCOUNT_ID, GRAPHQL_API_KEY)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "717830c1-02e7-4fa2-b92a-a231c0e046cc", + "metadata": {}, + "outputs": [], + "source": [ + "# more information: https://docs.moveo.ai/docs/analytics/brain_session_duration\n", + "query = \"\"\"\n", + "\n", + "query BrainSessionDuration(\n", + " $accountId: uuid\n", + " $deskIds: _uuid\n", + " $brainIds: _uuid\n", + " $channels: _text\n", + " $startDate: timestamp\n", + " $endDate: timestamp\n", + " $tags: _text\n", + " $isTest: Boolean\n", + " $limit: Int\n", + ") {\n", + " rows: brain_session_duration(\n", + " limit: $limit\n", + " args: {\n", + " start_time: $startDate\n", + " end_time: $endDate\n", + " account_id: $accountId\n", + " brain_parent_ids: $brainIds\n", + " desk_ids: $deskIds\n", + " channels: $channels\n", + " tags: $tags\n", + " is_test: $isTest\n", + " }\n", + " ) {\n", + " average_duration\n", + " average_duration_contained\n", + " average_duration_non_contained\n", + " average_duration_covered\n", + " average_duration_non_covered\n", + " }\n", + "}\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bf3a40da-771c-4801-b855-b5d12cadbc34", + "metadata": {}, + "outputs": [], + "source": [ + "# Query variables (substitute the desired dates)\n", + "account_id = ACCOUNT_ID\n", + "start_date = \"2024-02-20\"\n", + "end_date = \"2024-02-25\"\n", + "variables = {\"accountId\": account_id, \"startDate\": start_date, \"endDate\": end_date}" + ] + }, + { + "cell_type": "markdown", + "id": "5bea5dfd-f5c7-4dee-a981-21baa881ba6d", + "metadata": {}, + "source": [ + "### For all brains" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9eecb71c-1f4c-48ae-abdf-705d01a168cc", + "metadata": {}, + "outputs": [], + "source": [ + "# execute_query receives as arguments the GraphQL client, query and corresponding variables (dictionary)\n", + "session_duration_all_brains = execute_query(client, query, variables)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "7848e72e-fb0a-4e72-9a8c-9bed3e40394b", + "metadata": {}, + "outputs": [], + "source": [ + "print(session_duration_all_brains)" + ] + }, + { + "cell_type": "markdown", + "id": "b88b88c9-cb28-41a4-8313-169b918e72d7", + "metadata": {}, + "source": [ + "### For specific Brains" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "69629723-1b4f-4f40-8372-59ba47c27c1c", + "metadata": {}, + "outputs": [], + "source": [ + "# substitute the Brain Ids for which you want to get the average session duration\n", + "brain_ids = [\n", + " \"756772cb-d958-40c7-9b4c-0c1378d53989\",\n", + " \"c2fe9800-781f-4b6f-b02e-1c3453dc77db\",\n", + "]\n", + "variables[\"brainIds\"] = serialize_list_variable(brain_ids)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "096fbdb4-941a-4933-966c-080560ac59ea", + "metadata": {}, + "outputs": [], + "source": [ + "session_duration_specific_brains = execute_query(client, query, variables)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8b404298-e2bb-4f0f-9aa1-0bbc24dd7caf", + "metadata": {}, + "outputs": [], + "source": [ + "session_duration_specific_brains" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "110dea71-8cb2-4b17-83a5-a2fdb505163f", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a84638a8-e2da-4d17-899e-3084dadbf9d5", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.12" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/analytics/utils/__init__.py b/notebooks/analytics/utils/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/notebooks/analytics/utils/common.py b/notebooks/analytics/utils/common.py new file mode 100644 index 0000000..5283126 --- /dev/null +++ b/notebooks/analytics/utils/common.py @@ -0,0 +1,91 @@ +from typing import Dict, List + +import requests +from python_graphql_client import GraphqlClient +from utils.logger import logger + + +def initialize_graphql_clinet(account_id: str, api_key: str) -> GraphqlClient: + """ + Initializes a Graph QL client + + Args: + account_id (str): The Moveo account ID. + api_key (str): The API key for authentication. + + Returns: + list: List of logs retrieved from the API. + """ + client = GraphqlClient( + endpoint="https://logs.moveo.ai/v1/graphql", + headers={ + "Authorization": f"apikey {api_key}", + "X-Moveo-Account-Id": account_id, + }, + ) + + return client + + +def execute_query(client: GraphqlClient, query: str, variables: Dict) -> list: + """ + Fetch data from the Analytics API for a given session ID. + + Args: + client (GraphqlClient): GraphQL client + query (str): The GraphQL query. More information: + https://docs.moveo.ai/docs/analytics/api_overview + variables (dict): A dictionary with key = variable name of the query + and value = the variable value + + Returns: + list: List of logs retrieved from the API. + """ + + try: + raw_logs: dict = client.execute( + query=query, + variables=variables, + ) + except requests.exceptions.HTTPError as e: + if e.response.status_code == 404: + logger.warning("Received a 404 from the GrapgQL API", variables=variables) + return [] + logger.error( + f"Could not fetch content from the GraphQL API. Got error: {str(e)}", + variables=variables, + ) + return [] + except ValueError as e: + # Handle the JSON parsing error + logger.error( + f"Error parsing JSON response from the GraphQL API. Got error: {e}", + variables=variables, + ) + return [] + + # in case of error, raw_logs is the error message + if errors := raw_logs.get("errors"): + logger.error( + f"Unable to get result from GraphQL API. Got errors: {errors}", + variables=variables, + ) + return [] + + return raw_logs["data"]["rows"] + + +def serialize_list_variable(string_list: List[str]) -> str: + """ + Returns a serialized version of the input list of strings to be passed + as GraphQL variables + Args: + string_list (List[str]): the input strings + Returns: + a serialized string that is compatible with GraphQL + """ + # Format each string in the list to be double-quoted + formatted_strings = [f'"{s}"' for s in string_list] + # Join the formatted strings with a comma and space + # and enclose them in curly braces + return "{" + ", ".join(formatted_strings) + "}" diff --git a/notebooks/analytics/utils/logger.py b/notebooks/analytics/utils/logger.py new file mode 100644 index 0000000..12e08d3 --- /dev/null +++ b/notebooks/analytics/utils/logger.py @@ -0,0 +1,13 @@ +import structlog + +structlog.configure( + processors=[ + structlog.processors.StackInfoRenderer(), + structlog.dev.set_exc_info, + structlog.dev.ConsoleRenderer(colors=False), + ], + context_class=dict, + logger_factory=structlog.PrintLoggerFactory(), + cache_logger_on_first_use=False, +) +logger = structlog.get_logger() diff --git a/notebooks/zendesk/dialog_flow_analysis.ipynb b/notebooks/zendesk/dialog_flow_analysis.ipynb index d3f1257..3318264 100644 --- a/notebooks/zendesk/dialog_flow_analysis.ipynb +++ b/notebooks/zendesk/dialog_flow_analysis.ipynb @@ -25,11 +25,14 @@ "source": [ "import os\n", "\n", - "from utils.dialog_flow_analysis.common import (DETRACTORS_UPPER_LIMIT,\n", - " PROMOTERS_LOWER_LIMIT,\n", - " RATING_MAX, RATING_MIN,\n", - " analyze_flows,\n", - " extract_flows_from_session_id)\n", + "from utils.dialog_flow_analysis.common import (\n", + " DETRACTORS_UPPER_LIMIT,\n", + " PROMOTERS_LOWER_LIMIT,\n", + " RATING_MAX,\n", + " RATING_MIN,\n", + " analyze_flows,\n", + " extract_flows_from_session_id,\n", + ")\n", "from utils.dialog_flow_analysis.zendesk import match_zendesk_id_to_session_id\n", "from utils.logger import logger\n", "\n",