From 7688229f7cb156c711c6b34f922710dad92cee77 Mon Sep 17 00:00:00 2001 From: Tim Peters Date: Sat, 17 Feb 2001 05:58:44 +0000 Subject: SF patch #103808: doctest.py docs Checking in Moshe's patch after rewrapping some paragraphs (to consume fewer columns) and repairing that I/2.**J lost the I. --- Doc/lib/libdoctest.tex | 428 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 428 insertions(+) create mode 100644 Doc/lib/libdoctest.tex diff --git a/Doc/lib/libdoctest.tex b/Doc/lib/libdoctest.tex new file mode 100644 index 0000000..d4e3170 --- /dev/null +++ b/Doc/lib/libdoctest.tex @@ -0,0 +1,428 @@ +\section{\module{doctest} --- + Test docstrings represent reality} + +\declaremodule{standard}{doctest} +\moduleauthor{Tim Peters}{tim_one@users.sourceforge.net} +\sectionauthor{Tim Peters}{tim_one@users.sourceforge.net} +\sectionauthor{Moshe Zadka}{moshez@debian.org} + +\modulesynopsis{A framework for verifying examples in docstrings.} + +The \module{doctest} module searches a module's docstrings for text that looks +like an interactive Python session, then executes all such sessions to verify +they still work exactly as shown. Here's a complete but small example: + +\begin{verbatim} +""" +This is module example. + +Example supplies one function, factorial. For example, + +>>> factorial(5) +120 +""" + +def factorial(n): + """Return the factorial of n, an exact integer >= 0. + + If the result is small enough to fit in an int, return an int. + Else return a long. + + >>> [factorial(n) for n in range(6)] + [1, 1, 2, 6, 24, 120] + >>> [factorial(long(n)) for n in range(6)] + [1, 1, 2, 6, 24, 120] + >>> factorial(30) + 265252859812191058636308480000000L + >>> factorial(30L) + 265252859812191058636308480000000L + >>> factorial(-1) + Traceback (most recent call last): + ... + ValueError: n must be >= 0 + + Factorials of floats are OK, but the float must be an exact integer: + >>> factorial(30.1) + Traceback (most recent call last): + ... + ValueError: n must be exact integer + >>> factorial(30.0) + 265252859812191058636308480000000L + + It must also not be ridiculously large: + >>> factorial(1e100) + Traceback (most recent call last): + ... + OverflowError: n too large + """ + +\end{verbatim} +% allow LaTeX to break here. +\begin{verbatim} + + import math + if not n >= 0: + raise ValueError("n must be >= 0") + if math.floor(n) != n: + raise ValueError("n must be exact integer") + if n+1 == n: # e.g., 1e300 + raise OverflowError("n too large") + result = 1 + factor = 2 + while factor <= n: + try: + result *= factor + except OverflowError: + result *= long(factor) + factor += 1 + return result + +def _test(): + import doctest, example + return doctest.testmod(example) + +if __name__ == "__main__": + _test() +\end{verbatim} + +If you run \file{example.py} directly from the command line, doctest works +its magic: + +\begin{verbatim} +$ python example.py +$ +\end{verbatim} + +There's no output! That's normal, and it means all the examples worked. +Pass \code{-v} to the script, and doctest prints a detailed log of what it's +trying, and prints a summary at the end: + +\begin{verbatim} +$ python example.py -v +Running example.__doc__ +Trying: factorial(5) +Expecting: 120 +ok +0 of 1 examples failed in example.__doc__ +Running example.factorial.__doc__ +Trying: [factorial(n) for n in range(6)] +Expecting: [1, 1, 2, 6, 24, 120] +ok +Trying: [factorial(long(n)) for n in range(6)] +Expecting: [1, 1, 2, 6, 24, 120] +ok +Trying: factorial(30) +Expecting: 265252859812191058636308480000000L +ok +\end{verbatim} + +And so on, eventually ending with: + +\begin{verbatim} +Trying: factorial(1e100) +Expecting: +Traceback (most recent call last): + ... +OverflowError: n too large +ok +0 of 8 examples failed in example.factorial.__doc__ +2 items passed all tests: + 1 tests in example + 8 tests in example.factorial +9 tests in 2 items. +9 passed and 0 failed. +Test passed. +$ +\end{verbatim} + +That's all you need to know to start making productive use of doctest! Jump +in. The docstrings in doctest.py contain detailed information about all +aspects of doctest, and we'll just cover the more important points here. + +\subsection{Normal Usage} + +In normal use, end each module \module{M} with: + +\begin{verbatim} +def _test(): + import doctest, M # replace M with your module's name + return doctest.testmod(M) # ditto + +if __name__ == "__main__": + _test() +\end{verbatim} + +Then running the module as a script causes the examples in the docstrings +to get executed and verified: + +\begin{verbatim} +python M.py +\end{verbatim} + +This won't display anything unless an example fails, in which case the +failing example(s) and the cause(s) of the failure(s) are printed to stdout, +and the final line of output is \code{"Test failed."}. + +Run it with the \code{-v} switch instead: + +\begin{verbatim} +python M.py -v +\end{verbatim} + +and a detailed report of all examples tried is printed to \var{stdout}, +along with assorted summaries at the end. + +You can force verbose mode by passing \code{verbose=1} to testmod, or +prohibit it by passing \code{verbose=0}. In either of those cases, +\var{sys.argv} is not examined by testmod. + +In any case, testmod returns a 2-tuple of ints \var{(f, t)}, where \var{f} +is the number of docstring examples that failed and \var{t} is the total +number of docstring examples attempted. + +\subsection{Which Docstrings Are Examined?} + +See \file{docstring.py} for all the details. They're unsurprising: the +module docstring, and all function, class and method docstrings are +searched, with the exception of docstrings attached to objects with private +names. + +In addition, if \var{M.__test__} exists and "is true", it must be a dict, +and each entry maps a (string) name to a function object, class object, or +string. Function and class object docstrings found from \var{M.__test__} +are searched even if the name is private, and strings are searched directly +as if they were docstrings. In output, a key \var{K} in \var{M.__test__} +appears with name + +\begin{verbatim} + .__test__.K +\end{verbatim} + +Any classes found are recursively searched similarly, to test docstrings in +their contained methods and nested classes. While private names reached +from \module{M}'s globals are skipped, all names reached from +\var{M.__test__} are searched. + +\subsection{What's the Execution Context?} + +By default, each time testmod finds a docstring to test, it uses a +{\em copy} of \module{M}'s globals, so that running tests on a module +doesn't change the module's real globals, and so that one test in +\module{M} can't leave behind crumbs that accidentally allow another test +to work. This means examples can freely use any names defined at top-level +in \module{M}, and names defined earlier in the docstring being run. It +also means that sloppy imports (see below) can cause examples in external +docstrings to use globals inappropriate for them. + +You can force use of your own dict as the execution context by passing +\code{globs=your_dict} to \function{testmod()} instead. Presumably this +would be a copy of \var{M.__dict__} merged with the globals from other +imported modules. + +\subsection{What About Exceptions?} + +No problem, as long as the only output generated by the example is the +traceback itself. For example: + +\begin{verbatim} + >>> [1, 2, 3].remove(42) + Traceback (most recent call last): + File "", line 1, in ? + ValueError: list.remove(x): x not in list + >>> +\end{verbatim} + +Note that only the exception type and value are compared (specifically, +only the last line in the traceback). The various \code{"File"} lines in +between can be left out (unless they add significantly to the documentation +value of the example). + +\subsection{Advanced Usage} + +\function{testmod()} actually creates a local instance of class +\class{doctest.Tester}, runs appropriate methods of that class, and merges +the results into global \class{Tester} instance \var{doctest.master}. + +You can create your own instances of \class{doctest.Tester}, and so build +your own policies, or even run methods of \var{doctest.master} directly. +See \var{doctest.Tester.__doc__} for details. + + +\subsection{How are Docstring Examples Recognized?} + +In most cases a copy-and-paste of an interactive console session works fine +--- just make sure the leading whitespace is rigidly consistent (you can mix +tabs and spaces if you're too lazy to do it right, but doctest is not in +the business of guessing what you think a tab means). + +\begin{verbatim} + >>> # comments are ignored + >>> x = 12 + >>> x + 12 + >>> if x == 13: + ... print "yes" + ... else: + ... print "no" + ... print "NO" + ... print "NO!!!" + ... + no + NO + NO!!! + >>> +\end{verbatim} + +Any expected output must immediately follow the final \code{">>>"} or +\code{"..."} line containing the code, and the expected output (if any) +extends to the next \code{">>>"} or all-whitespace line. That's it. + +The fine print: + +\begin{itemize} + +\item Expected output cannot contain an all-whitespace line, since such a + line is taken to signal the end of expected output. + +\item Output to stdout is captured, but not output to stderr (exception + tracebacks are captured via a different means). + +\item If you continue a line via backslashing in an interactive session, or + for any other reason use a backslash, you need to double the backslash in + the docstring version. This is simply because you're in a string, and so + the backslash must be escaped for it to survive intact. Like: + +\begin{verbatim} +>>> if "yes" == \\ +... "y" + \\ +... "es": +... print 'yes' +yes +\end{verbatim} + +The starting column doesn't matter: + +\begin{verbatim} +>>> assert "Easy!" + >>> import math + >>> math.floor(1.9) + 1.0 +\end{verbatim} + +and as many leading whitespace characters are stripped from the expected +output as appeared in the initial ">>>" line that triggered it. + +\subsection{Warnings} + +\begin{enumerate} + +\item Sloppy imports can cause trouble; e.g., if you do + +\begin{verbatim} +from XYZ import XYZclass +\end{verbatim} + +then \class{XYZclass} is a name in \var{M.__dict__} too, and doctest has no +way to know that \class{XYZclass} wasn't *defined* in \module{M}. So it may +try to execute the examples in \class{XYZclass}'s docstring, and those in +turn may require a different set of globals to work correctly. I prefer to +do \code{import *}- friendly imports, a la + +\begin{verbatim} +from XYZ import XYZclass as _XYZclass +\end{verbatim} + +and then the leading underscore makes \class{_XYZclass} a private name so +testmod skips it by default. Other approaches are described in +\file{doctest.py}. + +\item \module{doctest} is serious about requiring exact matches in expected + output. If even a single character doesn't match, the test fails. This + will probably surprise you a few times, as you learn exactly what Python + does and doesn't guarantee about output. For example, when printing a + dict, Python doesn't guarantee that the key-value pairs will be printed + in any particular order, so a test like + +% Hey! What happened to Monty Python examples? +\begin{verbatim} + >>> foo() + {"Hermione": "hippogryph", "Harry": "broomstick"} + >>> +\end{verbatim} + +is vulnerable! One workaround is to do + +\begin{verbatim} + >>> foo() == {"Hermione": "hippogryph", "Harry": "broomstick"} + 1 + >>> +\end{verbatim} + +instead. Another is to do + +\begin{verbatim} + >>> d = foo().items() + >>> d.sort() + >>> d + [('Harry', 'broomstick'), ('Hermione', 'hippogryph')] +\end{verbatim} + +There are others, but you get the idea. + +Another bad idea is to print things that embed an object address, like + +\begin{verbatim} + >>> id(1.0) # certain to fail some of the time + 7948648 + >>> +\end{verbatim} + +Floating-point numbers are also subject to small output variations across +platforms, because Python defers to the platform C library for float +formatting, and C libraries vary widely in quality here. + +\begin{verbatim} + >>> 1./7 # risky + 0.14285714285714285 + >>> print 1./7 # safer + 0.142857142857 + >>> print round(1./7, 6) # much safer + 0.142857 +\end{verbatim} + +Numbers of the form \code{I/2.**J} are safe across all platforms, and I +often contrive doctest examples to produce numbers of that form: + +\begin{verbatim} + >>> 3./4 # utterly safe + 0.75 +\end{verbatim} + +Simple fractions are also easier for people to understand, and that makes +for better documentation. + + +\subsection{Soapbox} + +The first word in doctest is "doc", and that's why the author wrote +doctest: to keep documentation up to date. It so happens that doctest +makes a pleasant unit testing environment, but that's not its primary +purpose. + +Choose docstring examples with care. There's an art to this that needs to +be learned --- it may not be natural at first. Examples should add genuine +value to the documentation. A good example can often be worth many words. +If possible, show just a few normal cases, show endcases, show interesting +subtle cases, and show an example of each kind of exception that can be +raised. You're probably testing for endcases and subtle cases anyway in an +interactive shell: doctest wants to make it as easy as possible to capture +those sessions, and will verify they continue to work as designed forever +after. + +If done with care, the examples will be invaluable for your users, and will +pay back the time it takes to collect them many times over as the years go +by and "things change". I'm still amazed at how often one of my doctest +examples stops working after a "harmless" change. + +For exhaustive testing, or testing boring cases that add no value to the +docs, define a \var{__test__} dict instead. That's what it's for. -- cgit v0.12